-
Notifications
You must be signed in to change notification settings - Fork 177
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
Fixing some silent bugs in Arabic Custom Tasks #556
base: main
Are you sure you want to change the base?
Conversation
Fix alghafa prompt function by explicitly determining the list of choices based on task_name. Not all subsets of AlGhafa Native share same columns
Co-authored-by: Clémentine Fourrier <[email protected]>
Fix to `KeyError: 'sol3'` and `TypeError: Doc.__init__() got an unexpected keyword argument 'target_for_fewshot_sorting'`
correct prompt function
Hey @alielfilali01 ! Is is this ready for review ? |
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
Yes @NathanHB but apparently i need to fix the checks again 🥲 i always forget that |
Hey @NathanHB, the formatting is fixed with pre-commit hooks ! Thank you and sorry for taking too long on this one. I guess we can approve it and the checks should pass now |
This PR is meant to correct the implementation of MadinahQA which was populated without context. Correct the metric for AraTrust and Fix a silent bug in AlGhafa task which was incorrectly handling indexes.
Also remove the exams subset from alghafa suite in examples/tasks/OALL-2-Tasks txt file.
Merging this PR will allow the community to replicate the results displayed in OALL-2