{
  "architectures": [
    "LLaVABaselineModelForConditionalGeneration"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "modeling_llava_baseline.LLaVABaselineConfig",
    "AutoModelForCausalLM": "modeling_llava_baseline.LLaVABaselineModelForConditionalGeneration"
  },
  "dtype": "bfloat16",
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "image_token_id": 151655,
  "initializer_range": 0.02,
  "intermediate_size": 22016,
  "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",
    "full_attention",
    "full_attention",
    "full_attention",
    "full_attention"
  ],
  "llm_path": "/user/yutianyu/Qwen3-0.6B",
  "max_position_embeddings": 32768,
  "max_window_layers": 28,
  "model_type": "llava_baseline",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pad_token_id": 151643,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "sliding_window": null,
  "tie_word_embeddings": true,
  "transformers_version": "4.57.1",
  "use_cache": false,
  "use_sliding_window": false,
  "video_token_id": 151656,
  "vision_end_token_id": 151653,
  "vision_start_token_id": 151652,
  "vision_token_id": 151654,
  "vit_path": "/user/yutianyu/Qwen2.5-VL-3B-Instruct",
  "vocab_size": 151936
}