Skip to content

Pull requests: opendilab/LightRFT

Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

refactor(nyz): audio language model RL pipeline refactor Cleanup, formatting, or restructuring of existing code.
#58 opened Apr 14, 2026 by PaParaZz1 Member Loading…
4 tasks done
feature(zsa): add a minimal general ORM RL example on Geo3K documentation Improvements or additions to documentation enhancement New feature or request
#56 opened Apr 9, 2026 by HansBug Member Loading…
24 of 30 tasks
feature(zsh): migrate URSA-MATH stage3 training to LightRFT documentation Improvements or additions to documentation enhancement New feature or request
#53 opened Mar 18, 2026 by HansBug Member Draft
63 of 80 tasks
feature(sunjx): implement dynamic sampling strategy in DAPO enhancement New feature or request
#51 opened Mar 7, 2026 by Jiaxuan-Sun Contributor Loading…
feature(sunjx): add GSPO and GMPO algorithms support enhancement New feature or request
#50 opened Mar 4, 2026 by Jiaxuan-Sun Contributor Loading…
feature(nyz): transfer meme rl training demo enhancement New feature or request
#49 opened Feb 26, 2026 by PaParaZz1 Member Loading…
WIP: feature(pu): adapt to npu device enhancement New feature or request
#39 opened Feb 9, 2026 by puyuan1996 Collaborator Loading…
feature(sunjx): add rejection sampling in grm_training
#38 opened Feb 6, 2026 by Jiaxuan-Sun Contributor Loading…
doc(sjx/pu): add init version of fast_exp_maker best practice documentation Improvements or additions to documentation
#37 opened Feb 3, 2026 by puyuan1996 Collaborator Loading…
feature(luyd): add partial rollout in training process enhancement New feature or request
#29 opened Jan 22, 2026 by AltmanD 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 Contributor Loading…
refactor(sunjx): refactor dataset and reward module refactor Cleanup, formatting, or restructuring of existing code.
#13 opened Dec 31, 2025 by Jiaxuan-Sun Contributor Loading…
ProTip! Follow long discussions with comments:>50.