-
Notifications
You must be signed in to change notification settings - Fork 5
Pull requests: opendilab/LightRFT
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
style(pu): add issue and PR template, fix fcheck, polish readme
documentation
Improvements or additions to documentation
style
Code or comments formatting
#20
opened Jan 5, 2026 by
puyuan1996
Loading…
refactor(sunjx): refactor loss-filter implementation
enhancement
New feature or request
refactor
Cleanup, formatting, or restructuring of existing code.
#17
opened Jan 1, 2026 by
Jiaxuan-Sun
Loading…
refacotr(sunjx): refactor advantage calculation logic
refactor
Cleanup, formatting, or restructuring of existing code.
#16
opened Dec 31, 2025 by
Jiaxuan-Sun
Loading…
WIP: polish(pu): adapt lightrft to latest versions of sglang vllm deepspeed
enhancement
New feature or request
#14
opened Dec 31, 2025 by
puyuan1996
Loading…
refactor(sunjx): refactor dataset and reward module
refactor
Cleanup, formatting, or restructuring of existing code.
#13
opened Dec 31, 2025 by
Jiaxuan-Sun
Loading…
feature(sunjx): add high entropy token selection
enhancement
New feature or request
#6
opened Dec 25, 2025 by
Jiaxuan-Sun
Loading…
feature(sunjx): add some analysis metrics to saved trajectories
enhancement
New feature or request
#5
opened Dec 25, 2025 by
Jiaxuan-Sun
Loading…
feat(wzn): add video support for reinforcement finetuning
enhancement
New feature or request
#4
opened Dec 25, 2025 by
zunian-wan
Loading…
feature(sunjx): add rejective sampling pipeline in t2i demo
enhancement
New feature or request
#3
opened Dec 25, 2025 by
Jiaxuan-Sun
Loading…
ProTip!
Exclude everything labeled
bug with -label:bug.