{
  "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": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 6144,
    "max_position_embeddings": 262144,
    "model_type": "qwen3_vl_text",
    "num_attention_heads": 16,
    "num_hidden_layers": 19,
    "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"
    },
    "tie_word_embeddings": true,
    "use_cache": true,
    "vocab_size": 151936
  },
  "tie_word_embeddings": true,
  "transformers_version": "5.8.1",
  "use_cache": true,
  "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_vision",
    "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,
  "eos_token_id": [
    151645,
    151643
  ],
  "quantization": {
    "group_size": 64,
    "bits": 2,
    "mode": "affine",
    "model.language_model.layers.0.mlp.down_proj": {
      "bits": 6,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.0.self_attn.k_proj": {
      "bits": 6,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.0.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.0.self_attn.q_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.0.self_attn.v_proj": {
      "bits": 6,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.1.mlp.down_proj": {
      "bits": 6,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.1.self_attn.k_proj": {
      "bits": 6,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.1.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.1.self_attn.q_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.1.self_attn.v_proj": {
      "bits": 6,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.2.mlp.down_proj": {
      "bits": 6,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.2.self_attn.k_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.2.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.2.self_attn.q_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.2.self_attn.v_proj": {
      "bits": 6,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.3.mlp.down_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.10.mlp.down_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.10.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.11.mlp.down_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.11.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.12.mlp.down_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.12.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.13.mlp.down_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.3.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.4.mlp.down_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.4.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.5.mlp.down_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.5.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.6.mlp.down_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.6.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.7.mlp.down_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.7.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.8.mlp.down_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.8.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.9.mlp.down_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.9.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    }
  },
  "quantization_config": {
    "group_size": 64,
    "bits": 2,
    "mode": "affine",
    "model.language_model.layers.0.mlp.down_proj": {
      "bits": 6,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.0.self_attn.k_proj": {
      "bits": 6,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.0.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.0.self_attn.q_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.0.self_attn.v_proj": {
      "bits": 6,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.1.mlp.down_proj": {
      "bits": 6,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.1.self_attn.k_proj": {
      "bits": 6,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.1.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.1.self_attn.q_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.1.self_attn.v_proj": {
      "bits": 6,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.2.mlp.down_proj": {
      "bits": 6,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.2.self_attn.k_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.2.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.2.self_attn.q_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.2.self_attn.v_proj": {
      "bits": 6,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.3.mlp.down_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.10.mlp.down_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.10.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.11.mlp.down_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.11.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.12.mlp.down_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.12.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.13.mlp.down_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.3.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.4.mlp.down_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.4.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.5.mlp.down_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.5.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.6.mlp.down_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.6.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.7.mlp.down_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.7.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.8.mlp.down_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.8.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.9.mlp.down_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    },
    "model.language_model.layers.9.self_attn.o_proj": {
      "bits": 5,
      "group_size": 64,
      "mode": "affine"
    }
  }
}