multimodal-vicuna-7b-v1.5-video-naivemc/config.json

{
  "_name_or_path": "/yeesuanAI05/thumt/cc/checkpoints/vicuna-7b-v1.5",
  "architectures": [
    "MultimodalLlamaForCausalLM"
  ],
  "bos_token_id": 1,
  "eos_token_id": 2,
  "freeze_mm_mlp_adapter": false,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "image_aspect_ratio": "pad",
  "image_grid_pinpoints": null,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "layer_local_tokens": false,
  "local_prefix_tokens": 0,
  "local_suffix_tokens": 0,
  "lora_alpha": 256,
  "lora_dropout": 0.05,
  "lora_r": 128,
  "lora_strategy": "same",
  "max_position_embeddings": 4096,
  "mm_audio_encoder": null,
  "mm_video_encoder": "/yeesuanAI05/thumt/cc/checkpoints/LanguageBind_Video_merge",
  "mm_video_hidden_size": 1024,
  "mm_video_projector_type": "mlp2x_gelu",
  "mm_video_select_feature": "patch",
  "mm_video_select_layer": -2,
  "mm_vision_encoder": null,
  "mm_vision_tower": null,
  "model_type": "multimodal",
  "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,
  "seperate_layernorm": false,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.31.0",
  "tune_mm_mlp_adapter": false,
  "use_cache": true,
  "vocab_size": 32000
}