minigpt4/configs/models/minigpt4_llama2.yaml

model:
  arch: minigpt4

  # vit encoder
  image_size: 224
  drop_path_rate: 0
  use_grad_checkpoint: False
  vit_precision: "fp16"
  freeze_vit: True
  has_qformer: False

  # generation configs
  prompt: ""

  llama_model: "/mnt/logiccheck/MiniGPT-4/Llama-2-7b-chat-hf"

preprocess:
    vis_processor:
        train:
          name: "blip2_image_train"
          image_size: 224
        eval:
          name: "blip2_image_eval"
          image_size: 224
    text_processor:
        train:
          name: "blip_caption"
        eval:
          name: "blip_caption"