{
  "_name_or_path": "/home/yz/myLISA/checkpoints/LISA-7B-v1",
  "architectures": [
    "LISAForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "freeze_mm_mlp_adapter": true,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "ignore_index": -100,
  "image_aspect_ratio": "square",
  "image_grid_pinpoints": null,
  "image_token_index": 32000,
  "initializer_range": 0.02,
  "intermediate_dropout": 0.0,
  "intermediate_size": 11008,
  "max_position_embeddings": 2048,
  "max_sequence_length": 2048,
  "mm_hidden_size": 1024,
  "mm_use_im_patch_token": false,
  "mm_use_im_start_end": true,
  "mm_vision_select_feature": "patch",
  "mm_vision_select_layer": -2,
  "mm_vision_tower": "openai/clip-vit-large-patch14",
  "model_type": "llava",
  "npr_pretrained_path": null,
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "out_dim": 256,
  "pad_token_id": 0,
  "pretrain_mm_mlp_adapter": null,
  "pretraining_tp": 1,
  "projector_hidden_act": "gelu",
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "text_config": {
    "model_type": "llama",
    "vocab_size": 32005
  },
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "train_mask_decoder": true,
  "transformers_version": "4.37.2",
  "tune_mm_mlp_adapter": false,
  "use_cache": false,
  "use_mm_proj": true,
  "vision_config": {
    "hidden_size": 1024,
    "image_size": 336,
    "intermediate_size": 4096,
    "model_type": "clip_vision_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 24,
    "patch_size": 14,
    "projection_dim": 768,
    "vocab_size": 32000
  },
  "vision_feature_layer": -2,
  "vision_feature_select_strategy": "default",
  "vision_tower": "openai/clip-vit-large-patch14",
  "vocab_size": 32005
}