Skip to content

🦜Enhance repetition penalty reward for language that cannot be split by whitespace #516

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.

Sign up for GitHub

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

Jump to bottom
Merged
merged 5 commits into from
Apr 30, 2025
Merged

🦜Enhance repetition penalty reward for language that cannot be split by whitespace #516

merged 5 commits into from
Apr 30, 2025
+35 −8

Conversation

binary-husky
Copy link
Contributor

@binary-husky binary-husky commented Mar 18, 2025 •
edited
Loading

  • keep original reward unchanged when language param is not specified
  • use jieba to split zh
  • add test to ensure modification is valid
  • leave space for adding word spliter for other language implementation

@binary-husky binary-husky changed the title 🦜Enhance repetition penalty reward for languages that cannot be split by whitespace 🦜Enhance repetition penalty reward for language that cannot be split by whitespace Mar 18, 2025
lewtun
lewtun approved these changes Mar 25, 2025
View reviewed changes
Copy link
Member

@lewtun lewtun left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for the extension to new languages @binary-husky ! LGTM with some small nits

@lewtun
Copy link
Member

lewtun commented Mar 25, 2025

Also, please run make style && make quality to make the CI happy :)

binary-husky and others added 2 commits March 31, 2025 14:07
@binary-husky @lewtun
Update src/open_r1/rewards.py
79876b1 
Co-authored-by: lewtun <lewis.c.tunstall@gmail.com>
@binary-husky @lewtun
Update src/open_r1/rewards.py
a2d4926 
Co-authored-by: lewtun <lewis.c.tunstall@gmail.com>
@lewtun
Copy link
Member

lewtun commented Mar 31, 2025

@binary-husky it seems the try/except block in your unit test is causing the CI to complain - would you mind fixing it please and then we can merge 🙏 !

@lewtun lewtun merged commit 65211f4 into huggingface:main Apr 30, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@lewtun lewtun lewtun approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@binary-husky @lewtun