Skip to content
Merged
Changes from 1 commit
Commits
Show all changes
20 commits
Select commit Hold shift + click to select a range
ea8d3db
Update rl_replacements.py grpo accumulation kwargs
pluesclues Sep 29, 2025
9e7c377
Update rl.py, remove bnpo default when setting dapo
pluesclues Sep 29, 2025
ec4a544
Merge branch 'unslothai:main' into GRPO_grad_accum_edits
pluesclues Oct 1, 2025
f3ef5e8
Update rl.py
pluesclues Oct 1, 2025
1bb1bf3
Update rl_replacements.py, add support for vllm importance sampling
pluesclues Oct 1, 2025
912e3a8
Merge branch 'unslothai:main' into GRPO_grad_accum_edits
pluesclues Oct 1, 2025
1df48b3
Update rl_replacements.py, added ability to get metrics
pluesclues Oct 1, 2025
f5a1ad0
Update rl_replacements.py send sampling per token logps to backend
pluesclues Oct 1, 2025
e512a73
Update rl_replacements.py, corrected if statement in monkey patch
pluesclues Oct 1, 2025
d4ae11b
Merge branch 'unslothai:main' into GRPO_grad_accum_edits
pluesclues Oct 6, 2025
7a3a684
Update rl_replacements.py, updating to handle nan cases as well
pluesclues Oct 6, 2025
04ab5ea
Update rl_replacements.py, imported text warp
pluesclues Oct 6, 2025
0049790
Merge branch 'unslothai:main' into GRPO_grad_accum_edits
pluesclues Oct 13, 2025
ac4cfd2
Update rl_replacements.py, yes
pluesclues Oct 13, 2025
7f9f72e
Merge branch 'unslothai:main' into GRPO_grad_accum_edits
pluesclues Oct 20, 2025
98a2bf5
Add error handling for sampling_per_token_logps
pluesclues Oct 20, 2025
2eb4a0b
Add delta check for use_vllm condition
pluesclues Oct 21, 2025
595c380
Refactor vision model flag to use is_vlm variable
pluesclues Oct 22, 2025
34eabe5
Merge branch 'main' into GRPO_grad_accum_edits
pluesclues Oct 22, 2025
b937489
Merge branch 'unslothai:main' into GRPO_grad_accum_edits
pluesclues Oct 28, 2025
File filter

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Merge branch 'unslothai:main' into GRPO_grad_accum_edits
  • Loading branch information
pluesclues authored Oct 1, 2025
commit 912e3a883cec25093bf6949ae21dd8f99951e118

This merge commit was added into this branch cleanly.

There are no new changes to show, but you can still view the diff.