vcgbench/config.json

{
  "_name_or_path": "lmsys/vicuna-7b-v1.5",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "config": {
    "freeze": false,
    "mm_tune": true,
    "vision_tune": false
  },
  "eos_token_id": 2,
  "freeze_mm_mlp_adapter": false,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "image_aspect_ratio": "pad",
  "image_grid_pinpoints": null,
  "image_mm_hidden_size": 1024,
  "image_mm_projector_type": "mlp2x_gelu",
  "image_mm_vision_tower": "openai/clip-vit-large-patch14-336",
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "mm_hidden_size": 1408,
  "mm_projector_lr": 2e-05,
  "mm_projector_type": "mlp2x_gelu",
  "mm_use_box_start_end": false,
  "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": "OpenGVLab/InternVideo2-Stage2_1B-224p-f4/InternVideo2-stage2_1b-224p-f4.pt",
  "model_type": "VideoGPT+",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "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": 8192,
  "tokenizer_padding_side": "right",
  "torch_dtype": "float16",
  "transformers_version": "4.41.0.dev0",
  "tune_mm_mlp_adapter": false,
  "use_cache": true,
  "use_mm_proj": true,
  "vocab_size": 32000
}