{
  "architectures": [
    "LlavaForConditionalGeneration"
  ],
  "image_seq_length": 576,
  "image_token_index": 32000,
  "model_type": "llava",
  "multimodal_projector_bias": true,
  "pad_token_id": 32001,
  "projector_hidden_act": "gelu",
  "text_config": {
    "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
    "architectures": [
      "MistralForCausalLM"
    ],
    "attention_dropout": 0.0,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 14336,
    "max_position_embeddings": 32768,
    "model_type": "mistral",
    "num_attention_heads": 32,
    "num_hidden_layers": 32,
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-05,
    "rope_theta": 1000000.0,
    "sliding_window": null,
    "torch_dtype": "bfloat16",
    "use_cache": true,
    "vocab_size": 32064
  },
  "torch_dtype": "bfloat16",
  "transformers_version": "4.53.0",
  "vision_config": {
    "attention_dropout": 0.0,
    "hidden_act": "quick_gelu",
    "hidden_size": 1024,
    "image_size": 336,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "layer_norm_eps": 1e-05,
    "model_type": "clip_vision_model",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 24,
    "patch_size": 14,
    "projection_dim": 768,
    "vocab_size": 32000
  },
  "vision_feature_layer": -2,
  "vision_feature_select_strategy": "default"
}