| { |
| "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": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 25600, |
| "max_position_embeddings": 262144, |
| "model_type": "qwen3_vl_text", |
| "num_attention_heads": 64, |
| "num_hidden_layers": 50, |
| "num_key_value_heads": 8, |
| "pad_token_id": null, |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "mrope_interleaved": true, |
| "mrope_section": [ |
| 24, |
| 20, |
| 20 |
| ], |
| "rope_theta": 5000000, |
| "rope_type": "default" |
| }, |
| "use_cache": true, |
| "vocab_size": 151936 |
| }, |
| "tie_word_embeddings": false, |
| "transformers_version": "5.14.1", |
| "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_vision", |
| "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": 151653, |
| "vision_start_token_id": 151652, |
| "quantization_config": { |
| "ignore": [ |
| "model.language_model.embed_tokens", |
| "model.language_model.layers.17.mlp.down_proj", |
| "model.language_model.layers.18.mlp.down_proj", |
| "model.language_model.layers.19.mlp.down_proj", |
| "model.language_model.layers.21.mlp.down_proj", |
| "model.language_model.layers.22.mlp.down_proj", |
| "model.language_model.layers.23.mlp.down_proj", |
| "model.language_model.layers.24.mlp.down_proj", |
| "model.language_model.layers.24.self_attn.o_proj", |
| "model.language_model.layers.25.mlp.down_proj", |
| "model.language_model.layers.25.self_attn.o_proj", |
| "model.language_model.layers.26.mlp.down_proj", |
| "model.language_model.layers.27.mlp.down_proj", |
| "model.language_model.layers.28.mlp.down_proj", |
| "model.language_model.layers.29.mlp.down_proj", |
| "model.language_model.layers.30.mlp.down_proj", |
| "model.language_model.layers.30.self_attn.o_proj", |
| "model.language_model.layers.31.self_attn.o_proj", |
| "model.language_model.layers.34.mlp.down_proj", |
| "model.language_model.layers.35.self_attn.o_proj", |
| "model.language_model.layers.36.mlp.down_proj", |
| "model.language_model.layers.37.self_attn.o_proj", |
| "model.language_model.layers.38.self_attn.o_proj", |
| "model.language_model.layers.40.self_attn.o_proj", |
| "model.language_model.layers.42.self_attn.o_proj", |
| "model.language_model.layers.43.self_attn.o_proj", |
| "model.language_model.layers.44.self_attn.o_proj", |
| "model.language_model.layers.45.self_attn.o_proj", |
| "model.language_model.layers.46.mlp.down_proj", |
| "model.language_model.layers.46.self_attn.o_proj", |
| "model.language_model.layers.47.self_attn.o_proj", |
| "model.language_model.layers.48.mlp.down_proj", |
| "model.language_model.layers.48.self_attn.o_proj", |
| "model.language_model.layers.49.mlp.down_proj", |
| "model.language_model.layers.49.self_attn.o_proj" |
| ], |
| "quant_algo": "FP8_PER_CHANNEL_PER_TOKEN", |
| "producer": { |
| "name": "modelopt", |
| "version": "0.45.0rc1.dev28+gc88b62bee.d20260625" |
| }, |
| "quant_method": "modelopt" |
| } |
| } |