{
  "_name_or_path": "YanweiLi/llama-vid-7b-full-224-long-video",
  "architectures": [
    "LlavaLlamaAttForCausalLM"
  ],
  "bert_type": "qformer_pretrain_freeze",
  "bos_token_id": 1,
  "compress_type": "mean_concat",
  "cross_att_freq": 2,
  "debug_use": false,
  "eos_token_id": 2,
  "freeze_mm_mlp_adapter": false,
  "fusion_type": "attention_concat_all_query",
  "hidden_act": "silu",
  "hidden_size": 4096,
  "image_aspect_ratio": "pad",
  "image_grid_pinpoints": null,
  "image_processor": "/content/LLaMA-VID/model_zoo/OpenAI/clip-vit-large-patch14",
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "max_token": 65536,
  "mm_hidden_size": 1408,
  "mm_projector_type": "mlp2x_gelu",
  "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": "/content/LLaMA-VID/model_zoo/LAVIS/eva_vit_g.pth",
  "model_type": "llava",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "num_qformer": 32,
  "pad_token_id": 0,
  "position_type": null,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 16.0,
    "type": "linear"
  },
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.31.0",
  "tune_mm_mlp_adapter": false,
  "use_cache": true,
  "use_mm_proj": true,
  "use_raw_query_trans": false,
  "vocab_size": 32000
}