config.json

{
  "_name_or_path": "",
  "model_cls": "InternVideo2_VideoChat2",
  "architectures": [
    "InternVideo2_VideoChat2"
  ],
  "attn_implementation": "eager",
  "auto_map": {
    "AutoConfig": "model_config.VideoChat2Config",
    "AutoModel": "modeling_videochat2.InternVideo2_VideoChat2"
  },
  "model_config": {
    "bridge": {
      "extra_num_query_token": 64,
      "name": "qformer",
      "num_query_token": 32,
      "qformer_attention_probs_dropout_prob": 0.1,
      "qformer_drop_path_rate": 0.2,
      "qformer_hidden_dropout_prob": 0.1
    },
    "freeze_bridge": false,
    "freeze_llm": false,
    "freeze_vision_encoder": false,
    "llm": {
      "lora_alpha": 32,
      "lora_dropout": 0.1,
      "lora_r": 16,
      "name": "internlm2_5_7b",
      "pretrained_llm_path": "internlm/internlm2_5-7b-chat-1m",
      "use_lora": true
    },
    "loss": {
      "use_vision_regression_loss": false
    },
    "pretrained_paths": {},
    "use_flash_attention": true,
    "vision_encoder": {
      "checkpoint_num": 48,
      "d_model": 1408,
      "encoder_embed_dim": 1408,
      "img_size": 224,
      "name": "internvideo2-1B",
      "num_frames": 8,
      "origin_num_frames": 4,
      "patch_size": 14,
      "pretrained": null,
      "sep_image_video_pos_embed": true,
      "tubelet_size": 1,
      "use_checkpoint": true,
      "vit_add_ln": true,
      "x_vis_only": true,
      "x_vis_return_idx": -2
    }
  },
  "torch_dtype": "float32",
  "transformers_version": "4.38.0",
  "use_cache": true
}