Last active
June 28, 2023 13:45
-
-
Save daskol/8fa9e1c93e410526ab53d9d649fbaf19 to your computer and use it in GitHub Desktop.
Download a repo from HuggingFace Hub with aria2c.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
"""Little script for generating a download list for fetching model weights and | |
configuration files of a model from HuggingFace Hub. With download list is | |
ready, you can easily fetch all files with throatling and supspending or | |
resuming with `aria2c` as an example: aria2c -c -i index.txt. | |
""" | |
from pathlib import Path | |
from argparse import ArgumentParser, Namespace | |
from huggingface_hub import HfApi, hf_hub_url | |
parser = ArgumentParser(description=__doc__) | |
parser.add_argument('--output-dir', | |
default=Path(''), | |
type=Path, | |
help='where to store files (default: cwd)') | |
parser.add_argument('model_id', help='model identifier in huggingface hub') | |
parser.add_argument('download_list', | |
default=Path('index.txt'), | |
type=Path, | |
nargs='?', | |
help='where to write download list (default: index.txt)') | |
def main(args: Namespace): | |
with open(args.download_list, 'w') as fout: | |
make_download_list(fout, args.model_id, args.output_dir) | |
def make_download_list(fout, model_id: str, output_dir: Path, hf_api=None): | |
if hf_api is None: | |
hf_api = HfApi() | |
model_info = hf_api.model_info(model_id) | |
model_dir = '--'.join(['model', *model_id.split('/')]) # repo_folder_name | |
output_dir = output_dir / model_dir / model_info.sha | |
for ent in model_info.siblings: | |
url = hf_hub_url(model_id, ent.rfilename) | |
path = output_dir / ent.rfilename | |
fout.write(url) | |
fout.write(f'\n out={path}\n') | |
if __name__ == '__main__': | |
main(parser.parse_args()) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment