eval_configs/tinygptv_stage1_2_3_eval.yaml

model:
  arch: minigpt4
  model_type: pretrain_vicuna0
  max_txt_len: 160
  bos_token_id: "###"
  low_resource: False
  prompt_template: '###Human: {} ###Assistant: '
  ckpt: 'TinyGPT-V_for_Stage3.pth'
  lora_r: 64
  lora_alpha: 16


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