{
  "architectures": [
    "RadSightQwen3ForCausalLM"
  ],
  "ct_vision_encoder": "nnunet",
  "dtype": "bfloat16",
  "eos_token_id": 151645,
  "image_aspect_ratio": "square",
  "image_size": -1,
  "image_token_id": 151655,
  "image_token_index": 151669,
  "image_token_length": 1,
  "is_alignment": false,
  "llm_lr": 1e-05,
  "max_frames": null,
  "mm_hidden_size": 1152,
  "mm_hidden_size_3d": 256,
  "mm_projector_3d_lr": 1e-05,
  "mm_projector_lr": 1e-05,
  "mm_projector_type": "mlp2x_gelu",
  "mm_projector_type_3d": "spp",
  "mm_vision_select_feature": "patch",
  "mm_vision_select_layer": -1,
  "model_type": "radsight_qwen3",
  "pad_token_id": 151643,
  "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": 2560,
    "initializer_range": 0.02,
    "intermediate_size": 9728,
    "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,
    "tie_word_embeddings": true,
    "use_cache": true,
    "vocab_size": 151936
  },
  "tie_word_embeddings": true,
  "tokenizer_model_max_length": 16384,
  "tokenizer_padding_side": "right",
  "transformers_version": "4.57.0",
  "use_cache": true,
  "use_flash_loss": false,
  "use_mm_proj": true,
  "use_token_compression": false,
  "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": 2560,
    "patch_size": 16,
    "spatial_merge_size": 2,
    "temporal_patch_size": 2
  },
  "vision_encoder": "/mnt/nas/liujianqin/hf_model/SigLIP-NaViT",
  "vision_encoder_3d_lr": 2e-06,
  "vision_encoder_lr": 2e-06,
  "vision_end_token_id": 151653,
  "vision_start_token_id": 151652
}