minigpt4/configs/datasets/template/default.yaml

 # Copyright (c) 2022, salesforce.com, inc.
 # All rights reserved.
 # SPDX-License-Identifier: BSD-3-Clause
 # For full license text, see the LICENSE file in the repo root or https://opensource.org/licenses/BSD-3-Clause

datasets:
  dataset_name: # same as the name of the train_config yaml file
    # data_dir: ${env.data_dir}/datasets
    data_type: images # let it be images for now even if it is videos

    build_info: # this is the information needed to build the dataset
      # Be careful not to append minus sign (-) before split to avoid itemizing
      ann_paths: [path/to/annotations_json] # list of paths to annotation files
      vis_root: path/to/videos_folder
      subtitles_path: path/to/subtitles_folder
      model_name: 'llama2' # Language Model Name (available: llama2, mistral)