| { |
| "architectures": [ |
| "Qwen3VLForConditionalGeneration" |
| ], |
| "dtype": "bfloat16", |
| "eos_token_id": [ |
| 151645, |
| 151643 |
| ], |
| "image_token_id": 151655, |
| "model_type": "qwen3_vl", |
| "quantization": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "quantization_config": { |
| "group_size": 64, |
| "bits": 4, |
| "mode": "affine" |
| }, |
| "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": 2048, |
| "initializer_range": 0.02, |
| "intermediate_size": 6144, |
| "max_position_embeddings": 262144, |
| "model_type": "qwen3_vl_text", |
| "num_attention_heads": 16, |
| "num_hidden_layers": 28, |
| "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, |
| "tie_word_embeddings": true, |
| "use_cache": true, |
| "vocab_size": 151936 |
| }, |
| "tie_word_embeddings": true, |
| "transformers_version": "4.57.6", |
| "video_token_id": 151656, |
| "vision_config": { |
| "deepstack_visual_indexes": [ |
| 5, |
| 11, |
| 17 |
| ], |
| "depth": 24, |
| "dtype": "bfloat16", |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_size": 1024, |
| "in_channels": 3, |
| "initializer_range": 0.02, |
| "intermediate_size": 4096, |
| "model_type": "qwen3_vl", |
| "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 |
| } |
