sbull-dell's picture
Upload folder using huggingface_hub
83b1c0e verified
{
"architectures": [
"Qwen3VLMoeForConditionalGeneration"
],
"dtype": "bfloat16",
"image_token_id": 151655,
"model_type": "qwen3_vl_moe",
"text_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"decoder_sparse_step": 1,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"max_position_embeddings": 262144,
"mlp_only_layers": [],
"model_type": "qwen3_vl_moe_text",
"moe_intermediate_size": 768,
"norm_topk_prob": true,
"num_attention_heads": 32,
"num_experts": 128,
"num_experts_per_tok": 8,
"num_hidden_layers": 48,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_interleaved": true,
"mrope_section": [
24,
20,
20
],
"rope_type": "default"
},
"rope_theta": 5000000,
"router_aux_loss_coef": 0.001,
"use_cache": true,
"vocab_size": 151936
},
"tie_word_embeddings": false,
"transformers_version": "4.57.1",
"video_token_id": 151656,
"vision_config": {
"deepstack_visual_indexes": [
8,
16,
24
],
"depth": 27,
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 1152,
"in_channels": 3,
"initializer_range": 0.02,
"intermediate_size": 4304,
"model_type": "qwen3_vl_moe",
"num_heads": 16,
"num_position_embeddings": 2304,
"out_hidden_size": 2048,
"patch_size": 16,
"spatial_merge_size": 2,
"temporal_patch_size": 2
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"quantization_config": {
"config_groups": {
"group_0": {
"input_activations": {
"dynamic": false,
"num_bits": 4,
"type": "float",
"group_size": 16
},
"weights": {
"dynamic": false,
"num_bits": 4,
"type": "float",
"group_size": 16
},
"targets": [
"Linear"
]
}
},
"ignore": [
"lm_head",
"model.language_model.layers.0.mlp.gate",
"model.language_model.layers.1.mlp.gate",
"model.language_model.layers.10.mlp.gate",
"model.language_model.layers.11.mlp.gate",
"model.language_model.layers.12.mlp.gate",
"model.language_model.layers.13.mlp.gate",
"model.language_model.layers.14.mlp.gate",
"model.language_model.layers.15.mlp.gate",
"model.language_model.layers.16.mlp.gate",
"model.language_model.layers.17.mlp.gate",
"model.language_model.layers.18.mlp.gate",
"model.language_model.layers.19.mlp.gate",
"model.language_model.layers.2.mlp.gate",
"model.language_model.layers.20.mlp.gate",
"model.language_model.layers.21.mlp.gate",
"model.language_model.layers.22.mlp.gate",
"model.language_model.layers.23.mlp.gate",
"model.language_model.layers.24.mlp.gate",
"model.language_model.layers.25.mlp.gate",
"model.language_model.layers.26.mlp.gate",
"model.language_model.layers.27.mlp.gate",
"model.language_model.layers.28.mlp.gate",
"model.language_model.layers.29.mlp.gate",
"model.language_model.layers.3.mlp.gate",
"model.language_model.layers.30.mlp.gate",
"model.language_model.layers.31.mlp.gate",
"model.language_model.layers.32.mlp.gate",
"model.language_model.layers.33.mlp.gate",
"model.language_model.layers.34.mlp.gate",
"model.language_model.layers.35.mlp.gate",
"model.language_model.layers.36.mlp.gate",
"model.language_model.layers.37.mlp.gate",
"model.language_model.layers.38.mlp.gate",
"model.language_model.layers.39.mlp.gate",
"model.language_model.layers.4.mlp.gate",
"model.language_model.layers.40.mlp.gate",
"model.language_model.layers.41.mlp.gate",
"model.language_model.layers.42.mlp.gate",
"model.language_model.layers.43.mlp.gate",
"model.language_model.layers.44.mlp.gate",
"model.language_model.layers.45.mlp.gate",
"model.language_model.layers.46.mlp.gate",
"model.language_model.layers.47.mlp.gate",
"model.language_model.layers.5.mlp.gate",
"model.language_model.layers.6.mlp.gate",
"model.language_model.layers.7.mlp.gate",
"model.language_model.layers.8.mlp.gate",
"model.language_model.layers.9.mlp.gate",
"model.visual*"
],
"quant_algo": "NVFP4",
"kv_cache_scheme": {
"dynamic": false,
"num_bits": 8,
"type": "float"
},
"producer": {
"name": "modelopt",
"version": "0.41.0rc2.dev61+g02c5f292f"
},
"quant_method": "modelopt"
}
}