| { |
| "architectures": [ |
| "Qwen3_5ForConditionalGeneration" |
| ], |
| "image_token_id": 248056, |
| "model_type": "qwen3_5", |
| "quantization_config": { |
| "config_groups": { |
| "group_0": { |
| "format": "pack-quantized", |
| "input_activations": null, |
| "output_activations": null, |
| "targets": [ |
| "re:.*linear_attn.*" |
| ], |
| "weights": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": false, |
| "group_size": 32, |
| "num_bits": 8, |
| "observer": "mse", |
| "observer_kwargs": {}, |
| "scale_dtype": null, |
| "strategy": "group", |
| "symmetric": true, |
| "type": "int", |
| "zp_dtype": null |
| } |
| }, |
| "group_1": { |
| "format": "pack-quantized", |
| "input_activations": null, |
| "output_activations": null, |
| "targets": [ |
| "re:.*self_attn.*", |
| "re:.*mlp.*" |
| ], |
| "weights": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": false, |
| "group_size": 32, |
| "num_bits": 4, |
| "observer": "mse", |
| "observer_kwargs": {}, |
| "scale_dtype": null, |
| "strategy": "group", |
| "symmetric": true, |
| "type": "int", |
| "zp_dtype": null |
| } |
| } |
| }, |
| "format": "pack-quantized", |
| "global_compression_ratio": null, |
| "ignore": [ |
| "model.visual.blocks.0.attn.qkv", |
| "model.visual.blocks.0.attn.proj", |
| "model.visual.blocks.0.mlp.linear_fc1", |
| "model.visual.blocks.0.mlp.linear_fc2", |
| "model.visual.blocks.1.attn.qkv", |
| "model.visual.blocks.1.attn.proj", |
| "model.visual.blocks.1.mlp.linear_fc1", |
| "model.visual.blocks.1.mlp.linear_fc2", |
| "model.visual.blocks.2.attn.qkv", |
| "model.visual.blocks.2.attn.proj", |
| "model.visual.blocks.2.mlp.linear_fc1", |
| "model.visual.blocks.2.mlp.linear_fc2", |
| "model.visual.blocks.3.attn.qkv", |
| "model.visual.blocks.3.attn.proj", |
| "model.visual.blocks.3.mlp.linear_fc1", |
| "model.visual.blocks.3.mlp.linear_fc2", |
| "model.visual.blocks.4.attn.qkv", |
| "model.visual.blocks.4.attn.proj", |
| "model.visual.blocks.4.mlp.linear_fc1", |
| "model.visual.blocks.4.mlp.linear_fc2", |
| "model.visual.blocks.5.attn.qkv", |
| "model.visual.blocks.5.attn.proj", |
| "model.visual.blocks.5.mlp.linear_fc1", |
| "model.visual.blocks.5.mlp.linear_fc2", |
| "model.visual.blocks.6.attn.qkv", |
| "model.visual.blocks.6.attn.proj", |
| "model.visual.blocks.6.mlp.linear_fc1", |
| "model.visual.blocks.6.mlp.linear_fc2", |
| "model.visual.blocks.7.attn.qkv", |
| "model.visual.blocks.7.attn.proj", |
| "model.visual.blocks.7.mlp.linear_fc1", |
| "model.visual.blocks.7.mlp.linear_fc2", |
| "model.visual.blocks.8.attn.qkv", |
| "model.visual.blocks.8.attn.proj", |
| "model.visual.blocks.8.mlp.linear_fc1", |
| "model.visual.blocks.8.mlp.linear_fc2", |
| "model.visual.blocks.9.attn.qkv", |
| "model.visual.blocks.9.attn.proj", |
| "model.visual.blocks.9.mlp.linear_fc1", |
| "model.visual.blocks.9.mlp.linear_fc2", |
| "model.visual.blocks.10.attn.qkv", |
| "model.visual.blocks.10.attn.proj", |
| "model.visual.blocks.10.mlp.linear_fc1", |
| "model.visual.blocks.10.mlp.linear_fc2", |
| "model.visual.blocks.11.attn.qkv", |
| "model.visual.blocks.11.attn.proj", |
| "model.visual.blocks.11.mlp.linear_fc1", |
| "model.visual.blocks.11.mlp.linear_fc2", |
| "model.visual.blocks.12.attn.qkv", |
| "model.visual.blocks.12.attn.proj", |
| "model.visual.blocks.12.mlp.linear_fc1", |
| "model.visual.blocks.12.mlp.linear_fc2", |
| "model.visual.blocks.13.attn.qkv", |
| "model.visual.blocks.13.attn.proj", |
| "model.visual.blocks.13.mlp.linear_fc1", |
| "model.visual.blocks.13.mlp.linear_fc2", |
| "model.visual.blocks.14.attn.qkv", |
| "model.visual.blocks.14.attn.proj", |
| "model.visual.blocks.14.mlp.linear_fc1", |
| "model.visual.blocks.14.mlp.linear_fc2", |
| "model.visual.blocks.15.attn.qkv", |
| "model.visual.blocks.15.attn.proj", |
| "model.visual.blocks.15.mlp.linear_fc1", |
| "model.visual.blocks.15.mlp.linear_fc2", |
| "model.visual.blocks.16.attn.qkv", |
| "model.visual.blocks.16.attn.proj", |
| "model.visual.blocks.16.mlp.linear_fc1", |
| "model.visual.blocks.16.mlp.linear_fc2", |
| "model.visual.blocks.17.attn.qkv", |
| "model.visual.blocks.17.attn.proj", |
| "model.visual.blocks.17.mlp.linear_fc1", |
| "model.visual.blocks.17.mlp.linear_fc2", |
| "model.visual.blocks.18.attn.qkv", |
| "model.visual.blocks.18.attn.proj", |
| "model.visual.blocks.18.mlp.linear_fc1", |
| "model.visual.blocks.18.mlp.linear_fc2", |
| "model.visual.blocks.19.attn.qkv", |
| "model.visual.blocks.19.attn.proj", |
| "model.visual.blocks.19.mlp.linear_fc1", |
| "model.visual.blocks.19.mlp.linear_fc2", |
| "model.visual.blocks.20.attn.qkv", |
| "model.visual.blocks.20.attn.proj", |
| "model.visual.blocks.20.mlp.linear_fc1", |
| "model.visual.blocks.20.mlp.linear_fc2", |
| "model.visual.blocks.21.attn.qkv", |
| "model.visual.blocks.21.attn.proj", |
| "model.visual.blocks.21.mlp.linear_fc1", |
| "model.visual.blocks.21.mlp.linear_fc2", |
| "model.visual.blocks.22.attn.qkv", |
| "model.visual.blocks.22.attn.proj", |
| "model.visual.blocks.22.mlp.linear_fc1", |
| "model.visual.blocks.22.mlp.linear_fc2", |
| "model.visual.blocks.23.attn.qkv", |
| "model.visual.blocks.23.attn.proj", |
| "model.visual.blocks.23.mlp.linear_fc1", |
| "model.visual.blocks.23.mlp.linear_fc2", |
| "model.visual.blocks.24.attn.qkv", |
| "model.visual.blocks.24.attn.proj", |
| "model.visual.blocks.24.mlp.linear_fc1", |
| "model.visual.blocks.24.mlp.linear_fc2", |
| "model.visual.blocks.25.attn.qkv", |
| "model.visual.blocks.25.attn.proj", |
| "model.visual.blocks.25.mlp.linear_fc1", |
| "model.visual.blocks.25.mlp.linear_fc2", |
| "model.visual.blocks.26.attn.qkv", |
| "model.visual.blocks.26.attn.proj", |
| "model.visual.blocks.26.mlp.linear_fc1", |
| "model.visual.blocks.26.mlp.linear_fc2", |
| "model.visual.merger.linear_fc1", |
| "model.visual.merger.linear_fc2", |
| "model.language_model.layers.0.linear_attn.in_proj_b", |
| "model.language_model.layers.0.linear_attn.in_proj_a", |
| "model.language_model.layers.1.linear_attn.in_proj_b", |
| "model.language_model.layers.1.linear_attn.in_proj_a", |
| "model.language_model.layers.2.linear_attn.in_proj_b", |
| "model.language_model.layers.2.linear_attn.in_proj_a", |
| "model.language_model.layers.4.linear_attn.in_proj_b", |
| "model.language_model.layers.4.linear_attn.in_proj_a", |
| "model.language_model.layers.5.linear_attn.in_proj_b", |
| "model.language_model.layers.5.linear_attn.in_proj_a", |
| "model.language_model.layers.6.linear_attn.in_proj_b", |
| "model.language_model.layers.6.linear_attn.in_proj_a", |
| "model.language_model.layers.8.linear_attn.in_proj_b", |
| "model.language_model.layers.8.linear_attn.in_proj_a", |
| "model.language_model.layers.9.linear_attn.in_proj_b", |
| "model.language_model.layers.9.linear_attn.in_proj_a", |
| "model.language_model.layers.10.linear_attn.in_proj_b", |
| "model.language_model.layers.10.linear_attn.in_proj_a", |
| "model.language_model.layers.12.linear_attn.in_proj_b", |
| "model.language_model.layers.12.linear_attn.in_proj_a", |
| "model.language_model.layers.13.linear_attn.in_proj_b", |
| "model.language_model.layers.13.linear_attn.in_proj_a", |
| "model.language_model.layers.14.linear_attn.in_proj_b", |
| "model.language_model.layers.14.linear_attn.in_proj_a", |
| "model.language_model.layers.16.linear_attn.in_proj_b", |
| "model.language_model.layers.16.linear_attn.in_proj_a", |
| "model.language_model.layers.17.linear_attn.in_proj_b", |
| "model.language_model.layers.17.linear_attn.in_proj_a", |
| "model.language_model.layers.18.linear_attn.in_proj_b", |
| "model.language_model.layers.18.linear_attn.in_proj_a", |
| "model.language_model.layers.20.linear_attn.in_proj_b", |
| "model.language_model.layers.20.linear_attn.in_proj_a", |
| "model.language_model.layers.21.linear_attn.in_proj_b", |
| "model.language_model.layers.21.linear_attn.in_proj_a", |
| "model.language_model.layers.22.linear_attn.in_proj_b", |
| "model.language_model.layers.22.linear_attn.in_proj_a", |
| "model.language_model.layers.24.linear_attn.in_proj_b", |
| "model.language_model.layers.24.linear_attn.in_proj_a", |
| "model.language_model.layers.25.linear_attn.in_proj_b", |
| "model.language_model.layers.25.linear_attn.in_proj_a", |
| "model.language_model.layers.26.linear_attn.in_proj_b", |
| "model.language_model.layers.26.linear_attn.in_proj_a", |
| "model.language_model.layers.28.linear_attn.in_proj_b", |
| "model.language_model.layers.28.linear_attn.in_proj_a", |
| "model.language_model.layers.29.linear_attn.in_proj_b", |
| "model.language_model.layers.29.linear_attn.in_proj_a", |
| "model.language_model.layers.30.linear_attn.in_proj_b", |
| "model.language_model.layers.30.linear_attn.in_proj_a", |
| "model.language_model.layers.32.linear_attn.in_proj_b", |
| "model.language_model.layers.32.linear_attn.in_proj_a", |
| "model.language_model.layers.33.linear_attn.in_proj_b", |
| "model.language_model.layers.33.linear_attn.in_proj_a", |
| "model.language_model.layers.34.linear_attn.in_proj_b", |
| "model.language_model.layers.34.linear_attn.in_proj_a", |
| "model.language_model.layers.36.linear_attn.in_proj_b", |
| "model.language_model.layers.36.linear_attn.in_proj_a", |
| "model.language_model.layers.37.linear_attn.in_proj_b", |
| "model.language_model.layers.37.linear_attn.in_proj_a", |
| "model.language_model.layers.38.linear_attn.in_proj_b", |
| "model.language_model.layers.38.linear_attn.in_proj_a", |
| "model.language_model.layers.40.linear_attn.in_proj_b", |
| "model.language_model.layers.40.linear_attn.in_proj_a", |
| "model.language_model.layers.41.linear_attn.in_proj_b", |
| "model.language_model.layers.41.linear_attn.in_proj_a", |
| "model.language_model.layers.42.linear_attn.in_proj_b", |
| "model.language_model.layers.42.linear_attn.in_proj_a", |
| "model.language_model.layers.44.linear_attn.in_proj_b", |
| "model.language_model.layers.44.linear_attn.in_proj_a", |
| "model.language_model.layers.45.linear_attn.in_proj_b", |
| "model.language_model.layers.45.linear_attn.in_proj_a", |
| "model.language_model.layers.46.linear_attn.in_proj_b", |
| "model.language_model.layers.46.linear_attn.in_proj_a", |
| "model.language_model.layers.48.linear_attn.in_proj_b", |
| "model.language_model.layers.48.linear_attn.in_proj_a", |
| "model.language_model.layers.49.linear_attn.in_proj_b", |
| "model.language_model.layers.49.linear_attn.in_proj_a", |
| "model.language_model.layers.50.linear_attn.in_proj_b", |
| "model.language_model.layers.50.linear_attn.in_proj_a", |
| "model.language_model.layers.52.linear_attn.in_proj_b", |
| "model.language_model.layers.52.linear_attn.in_proj_a", |
| "model.language_model.layers.53.linear_attn.in_proj_b", |
| "model.language_model.layers.53.linear_attn.in_proj_a", |
| "model.language_model.layers.54.linear_attn.in_proj_b", |
| "model.language_model.layers.54.linear_attn.in_proj_a", |
| "model.language_model.layers.56.linear_attn.in_proj_b", |
| "model.language_model.layers.56.linear_attn.in_proj_a", |
| "model.language_model.layers.57.linear_attn.in_proj_b", |
| "model.language_model.layers.57.linear_attn.in_proj_a", |
| "model.language_model.layers.58.linear_attn.in_proj_b", |
| "model.language_model.layers.58.linear_attn.in_proj_a", |
| "model.language_model.layers.60.linear_attn.in_proj_b", |
| "model.language_model.layers.60.linear_attn.in_proj_a", |
| "model.language_model.layers.61.linear_attn.in_proj_b", |
| "model.language_model.layers.61.linear_attn.in_proj_a", |
| "model.language_model.layers.62.linear_attn.in_proj_b", |
| "model.language_model.layers.62.linear_attn.in_proj_a", |
| "lm_head", |
| "mtp.fc" |
| ], |
| "kv_cache_scheme": null, |
| "quant_method": "compressed-tensors", |
| "quantization_status": "compressed", |
| "sparsity_config": {}, |
| "transform_config": {}, |
| "version": "0.14.1.dev20+g5d2f568" |
| }, |
| "text_config": { |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attn_output_gate": true, |
| "dtype": "bfloat16", |
| "eos_token_id": 248044, |
| "full_attention_interval": 4, |
| "head_dim": 256, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 17408, |
| "layer_types": [ |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention" |
| ], |
| "linear_conv_kernel_dim": 4, |
| "linear_key_head_dim": 128, |
| "linear_num_key_heads": 16, |
| "linear_num_value_heads": 48, |
| "linear_value_head_dim": 128, |
| "max_position_embeddings": 262144, |
| "mlp_only_layers": [], |
| "model_type": "qwen3_5_text", |
| "mtp_num_hidden_layers": 1, |
| "mtp_use_dedicated_embeddings": false, |
| "num_attention_heads": 24, |
| "num_hidden_layers": 64, |
| "num_key_value_heads": 4, |
| "rms_norm_eps": 1e-06, |
| "use_cache": true, |
| "vocab_size": 248320, |
| "mamba_ssm_dtype": "float32", |
| "rope_parameters": { |
| "mrope_interleaved": true, |
| "mrope_section": [ |
| 11, |
| 11, |
| 10 |
| ], |
| "rope_type": "default", |
| "rope_theta": 10000000, |
| "partial_rotary_factor": 0.25 |
| } |
| }, |
| "tie_word_embeddings": false, |
| "transformers_version": "4.57.0.dev0", |
| "video_token_id": 248057, |
| "vision_config": { |
| "deepstack_visual_indexes": [], |
| "depth": 27, |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_size": 1152, |
| "in_channels": 3, |
| "initializer_range": 0.02, |
| "intermediate_size": 4304, |
| "model_type": "qwen3_5", |
| "num_heads": 16, |
| "num_position_embeddings": 2304, |
| "out_hidden_size": 5120, |
| "patch_size": 16, |
| "spatial_merge_size": 2, |
| "temporal_patch_size": 2 |
| }, |
| "vision_end_token_id": 248054, |
| "vision_start_token_id": 248053 |
| } |
