Skip to content
New issue

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

#

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

Already on GitHub? # to your account

Jump to bottom

FIRE sampling added. #58

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

FIRE sampling added. #58

wants to merge 2 commits into from
+54 −10

Conversation

laonahongchen
Copy link

Add FIRE sampling from paper Flaming-hot Initiation with Regular Execution Sampling for Large Language Models (https://arxiv.org/abs/2410.21236) to the PPO trainer loop as an additional option to turn on.

@willem-bd willem-bd requested a review from PeterSH6 December 24, 2024 11:10
eric-haibin-lin
eric-haibin-lin reviewed Jan 13, 2025
View reviewed changes
Copy link
Collaborator

@eric-haibin-lin eric-haibin-lin left a comment •
edited
Loading

Choose a reason for hiding this comment

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

Sorry for the late review and thanks for the contribution! Would you mind introducing a new class inheriting vllmRollout, add the custom sampling logics? This way it'd be easier to maintain the codebase

# for free to join this conversation on GitHub. Already have an account? # to comment
Reviewers

@eric-haibin-lin eric-haibin-lin eric-haibin-lin left review comments

@PeterSH6 PeterSH6 Awaiting requested review from PeterSH6

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
@laonahongchen @eric-haibin-lin