{
  "architectures": [
    "Qwen2VisionForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "dtype": "bfloat16",
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 1536,
  "initializer_range": 0.02,
  "intermediate_size": 8960,
  "layer_types": [
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "max_position_embeddings": 131072,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 12,
  "num_hidden_layers": 28,
  "num_key_value_heads": 2,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": true,
  "transformers_version": "4.57.6",
  "use_cache": true,
  "use_mrope": false,
  "use_sliding_window": false,
  "vocab_size": 151936,
  "auto_map": {
    "AutoModelForCausalLM": "modeling_qwen2_vision.Qwen2VisionForCausalLM"
  },
  "vision_config": {
    "model_type": "dinov2",
    "hidden_size": 384,
    "num_hidden_layers": 12,
    "num_attention_heads": 6,
    "patch_size": 14,
    "image_size": 224,
    "mlp_ratio": 4,
    "dinov2_path": "D:/论文/Yxw/白盒/Qwen2.5-1.5B-Instruct/model_release/dinov2"
  }
}