{
    "_name_or_path": "llava-v1.6-vicuna-13b",
    "architectures": [
      "LlavaLlamaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 1,
    "eos_token_id": 2,
    "freeze_mm_mlp_adapter": false,
    "freeze_mm_vision_resampler": false,
    "hidden_act": "silu",
    "hidden_size": 5120,
    "image_aspect_ratio": "anyres",
    "image_crop_resolution": 224,
    "image_grid_pinpoints": [
      [
        336,
        672
      ],
      [
        672,
        336
      ],
      [
        672,
        672
      ],
      [
        1008,
        336
      ],
      [
        336,
        1008
      ]
    ],
    "image_split_resolution": 224,
    "initializer_range": 0.02,
    "intermediate_size": 13824,
    "max_length": 4096,
    "max_position_embeddings": 4096,
    "mm_hidden_size": 1024,
    "mm_patch_merge_type": "spatial_unpad",
    "mm_projector_lr": null,
    "mm_projector_type": "mlp2x_gelu",
    "mm_resampler_type": null,
    "mm_use_im_patch_token": false,
    "pretrain_mm_mlp_adapter": null,
    "mm_use_im_start_end": false,
    "mm_vision_select_feature": "patch",
    "mm_vision_select_layer": -2,
    "mm_vision_tower": "openai/clip-vit-large-patch14-336",
    "mm_vision_tower_lr": 2e-06,
    "model_type": "llava",
    "num_attention_heads": 40,
    "num_hidden_layers": 40,
    "num_key_value_heads": 40,
    "pad_token_id": 0,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 10000.0,
    "tie_word_embeddings": false,
    "tokenizer_model_max_length": 4096,
    "tokenizer_padding_side": "right",
    "transformers_version": "4.36.2",
    "tune_mm_mlp_adapter": false,
    "tune_mm_vision_resampler": false,
    "unfreeze_mm_vision_tower": true,
    "use_cache": true,
    "use_mm_proj": true,
    "vocab_size": 32000
  }