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

feat: anchored pref optimization #1928

Merged
merged 12 commits into from
Aug 14, 2024
Merged

Conversation

karel-contextual
Copy link
Contributor

Add APO objectives, specifically equation 7 and 8 of the APO paper (https://huggingface.co/papers/2408.06266)

@qgallouedec
Copy link
Member

Nice, thanks, I'll take the opportunity to update the documentations for the losses we already support (in another PR that I'd like to merge first)

@HuggingFaceDocBuilderDev

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.

@qgallouedec
Copy link
Member

#1929

@kashif
Copy link
Collaborator

kashif commented Aug 14, 2024

@karel-contextual can you kindly run:

pre-commit run --all-files

in the root dir of TRL to fix up the formatting

trl/trainer/dpo_trainer.py Outdated Show resolved Hide resolved
@qgallouedec
Copy link
Member

LGTM now, thanks @karel-contextual!

@qgallouedec qgallouedec merged commit a7dc892 into huggingface:main Aug 14, 2024
9 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants