{
  "architectures": [
    "LlavaLlamaForCausalLM"
  ],
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 5504,
  "max_position_embeddings": 8192,
  "freeze_mm_mlp_adapter": false,
  "image_aspect_ratio": "pad",
  "image_grid_pinpoints": null,
  "mm_hidden_size": 1024,
  "mm_projector_type": "mlp2x_gelu_Norm",
  "mm_use_im_patch_token": false,
  "mm_use_im_start_end": false,
  "mm_vision_select_feature": "patch",
  "mm_vision_select_layer": -2,
  "mm_vision_tower": "./chinese-clip-vit-large-patch14-336px",
  "model_type": "llava",
  "tune_mm_mlp_adapter": false,
  "tune_vision_tower": false,
  "use_mm_proj": true,

  "num_attention_heads": 16,
  "num_hidden_layers": 24,
  "num_key_value_heads": 16,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.34.0",
  "use_cache": true,
  "vocab_size": 151936,
  "attention_bias": true
}