| { |
| "architectures": [ |
| "Qwen3VLForConditionalGeneration" |
| ], |
| "dtype": "bfloat16", |
| "image_token_id": 151655, |
| "model_type": "qwen3_vl", |
| "text_config": { |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 151643, |
| "dtype": "bfloat16", |
| "eos_token_id": 151645, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "initializer_range": 0.02, |
| "intermediate_size": 12288, |
| "max_position_embeddings": 262144, |
| "model_type": "qwen3_vl_text", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 36, |
| "num_key_value_heads": 8, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": { |
| "mrope_interleaved": true, |
| "mrope_section": [ |
| 24, |
| 20, |
| 20 |
| ], |
| "rope_type": "default" |
| }, |
| "rope_theta": 5000000, |
| "use_cache": true, |
| "vocab_size": 151936 |
| }, |
| "tie_word_embeddings": false, |
| "transformers_version": "4.57.6", |
| "video_token_id": 151656, |
| "vision_config": { |
| "deepstack_visual_indexes": [ |
| 8, |
| 16, |
| 24 |
| ], |
| "depth": 27, |
| "dtype": "bfloat16", |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_size": 1152, |
| "in_channels": 3, |
| "initializer_range": 0.02, |
| "intermediate_size": 4304, |
| "model_type": "qwen3_vl", |
| "num_heads": 16, |
| "num_position_embeddings": 2304, |
| "out_hidden_size": 4096, |
| "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.visual.blocks.0.mlp*", |
| "model.visual.blocks.1.mlp*", |
| "model.visual.blocks.10.mlp*", |
| "model.visual.blocks.11.mlp*", |
| "model.visual.blocks.12.mlp*", |
| "model.visual.blocks.13.mlp*", |
| "model.visual.blocks.14.mlp*", |
| "model.visual.blocks.15.mlp*", |
| "model.visual.blocks.16.mlp*", |
| "model.visual.blocks.17.mlp*", |
| "model.visual.blocks.18.mlp*", |
| "model.visual.blocks.19.mlp*", |
| "model.visual.blocks.2.mlp*", |
| "model.visual.blocks.20.mlp*", |
| "model.visual.blocks.21.mlp*", |
| "model.visual.blocks.22.mlp*", |
| "model.visual.blocks.23.mlp*", |
| "model.visual.blocks.24.mlp*", |
| "model.visual.blocks.25.mlp*", |
| "model.visual.blocks.26.mlp*", |
| "model.visual.blocks.3.mlp*", |
| "model.visual.blocks.4.mlp*", |
| "model.visual.blocks.5.mlp*", |
| "model.visual.blocks.6.mlp*", |
| "model.visual.blocks.7.mlp*", |
| "model.visual.blocks.8.mlp*", |
| "model.visual.blocks.9.mlp*" |
| ], |
| "quant_algo": "NVFP4", |
| "producer": { |
| "name": "modelopt", |
| "version": "0.43.0" |
| }, |
| "quant_method": "modelopt" |
| } |
| } |