eval_configs/minigpt4_eval.yaml

model:
  arch: minigpt4
  model_type: pretrain_vicuna0
  max_txt_len: 160
  end_sym: "###"
  low_resource: True
  prompt_template: '###Human: {} ###Assistant: '
  ckpt: 'prerained_minigpt4_7b.pth'


datasets:
  cc_sbu_align:
    vis_processor:
      train:
        name: "blip2_image_eval"
        image_size: 224
    text_processor:
      train:
        name: "blip_caption"

run:
  task: image_text_pretrain