model:
  arch: minigpt_v2

  # vit encoder
  image_size: 448
  drop_path_rate: 0
  use_grad_checkpoint: False
  vit_precision: "fp16"
  freeze_vit: True

  # generation configs
  prompt: ""

  llama_model: "meta-llama/Llama-2-7b-chat-hf"
  lora_r: 64
  lora_alpha: 16


preprocess:
    vis_processor:
        train:
          name: "blip2_image_train"
          image_size: 448
        eval:
          name: "blip2_image_eval"
          image_size: 448
    text_processor:
        train:
          name: "blip_caption"
        eval:
          name: "blip_caption"