Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

❓ Why in run_squad.py using XLNet, CLS token is not set at the end ? #1088

Closed
astariul opened this issue Aug 23, 2019 · 2 comments
Closed
Labels

Comments

@astariul
Copy link
Contributor

astariul commented Aug 23, 2019

❓ Questions & Help

This line of the file run_squad.py create the features for the dataset.

No matter which model is used (BERT or XLNet), the function will create the format :

CLS A SEP B SEP

But for XLNet case, we want :

A SEP B SEP CLS


Isn' it wrong ? Did I miss something ?

@astariul astariul changed the title Why in run_squad.py using XLNet, CLS token is not set at the end ? ❓ Why in run_squad.py using XLNet, CLS token is not set at the end ? Aug 23, 2019
@thomwolf
Copy link
Member

Humm I think you are right.

The SquAD example looks a bit broken in pytorch-transformers, we will have to review it @LysandreJik.

@stale
Copy link

stale bot commented Oct 22, 2019

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

2 participants