mir/gpt-2-output-dataset
2
0
Fork 0
mirror of https://github.com/openai/gpt-2-output-dataset synced 2025-08-23 10:27:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

move to azure

Browse Source
This commit is contained in:
Jeff Wu 2021-02-11 13:10:14 -08:00
parent ddfecb3932
commit d6f4e2956b
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
download_dataset.py
View File

@ -17,7 +17,7 @@ for ds in [
]:
for split in ['train', 'valid', 'test']:
filename = ds + "." + split + '.jsonl'
r = requests.get("https://storage.googleapis.com/gpt-2/output-dataset/v1/" + filename, stream=True)
r = requests.get("https://openaipublic.blob.core.windows.net/gpt-2/output-dataset/v1/" + filename, stream=True)
with open(os.path.join(subdir, filename), 'wb') as f:
file_size = int(r.headers["content-length"])