config.json

{
  "X": [
    "Audio_asr",
    "Audio_caption",
    "Video",
    "Image"
  ],
  "_name_or_path": "/mnt/bn/tns-algo-video-public-my2/wangpeng.an/model/Meta-Llama-3.1-8B-Instruct",
  "architectures": [
    "LlavaLlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": [
    128001,
    128008,
    128009
  ],
  "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": 14336,
  "is_fusion": false,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "mm_audio_caption_tower": "/mnt/bn/tns-algo-video-public-my2/wangpeng.an/model/pretrained_model/LanguageBind_Audio",
  "mm_audio_tower": "/mnt/bn/tns-algo-video-public-my2/wangpeng.an/model/LanguageBind_Audio_Asr",
  "mm_hidden_size": 1024,
  "mm_image_tower": "/mnt/bn/tns-algo-video-public-my2/wangpeng.an/model/pretrained_model/LanguageBind_Image",
  "mm_projector_type": "mlp2x_gelu",
  "mm_use_x_patch_token": false,
  "mm_use_x_start_end": false,
  "mm_video_tower": "/mnt/bn/tns-algo-video-public-my2/wangpeng.an/model/pretrained_model/LanguageBind_Video_merge",
  "mm_vision_select_feature": "patch",
  "mm_vision_select_layer": -2,
  "model_type": "llava_llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 8.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "tokenizer_model_max_length": 3072,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.43.1",
  "tune_mm_mlp_adapter": false,
  "use_cache": true,
  "use_mm_proj": true,
  "vocab_size": 128256
}