eval_configs/video_llama_eval_withaudio.yaml

model:
  arch: video_llama
  model_type: pretrain_vicuna
  freeze_vit: True
  freeze_qformer: True
  max_txt_len: 512
  end_sym: "###"
  low_resource: False

  frozen_llama_proj: False

  llama_model: "Video-LLaMA-2-7B-Finetuned/llama-2-7b-chat-hf"
  imagebind_ckpt_path: "Video-LLaMA-2-7B-Finetuned"
  ckpt: "Video-LLaMA-2-7B-Finetuned/VL_LLaMA_2_7B_Finetuned.pth"
  ckpt_2: "Video-LLaMA-2-7B-Finetuned/AL_LLaMA_2_7B_Finetuned.pth"

  equip_audio_branch: True  # whether equips the audio branch
  fusion_head_layers: 2
  max_frame_pos: 32
  fusion_header_type: "seqTransf"


datasets:
  webvid:
    vis_processor:
      train:
        name: "alpro_video_eval"
        n_frms: 8
        image_size: 224
    text_processor:
      train:
        name: "blip_caption"

run:
  task: video_text_pretrain