-
Notifications
You must be signed in to change notification settings - Fork 2.9k
Pull requests: huggingface/trl
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Rewrite the TRL skill around the Python API
#6794
opened Aug 18, 2026 by
qgallouedec
Member
•
2/2
Loading…
Ship the TRL skill at the
.agents/skills convention and drop trl skills install
#6793
opened Aug 18, 2026 by
qgallouedec
Member
•
1/2
Loading…
Allow dict config fields to be set from the command line
#6792
opened Aug 18, 2026 by
qgallouedec
Member
Loading…
Drop ruff workaround from doc-builder pre-commit hook
#6790
opened Aug 18, 2026 by
albertvillanova
Member
•
Draft
Clarify generalized JSD endpoint definition
#6781
opened Aug 17, 2026 by
DaoyuanLi2816
Contributor
Loading…
6 of 8 tasks
Fix Nemotron 3 SFT example: add Mamba modules to LoRA targets
#6777
opened Aug 17, 2026 by
davidnichols-ops
Loading…
4 of 5 tasks
fix: surface NaN GRPO/RLOO steps in log_history
#6772
opened Aug 17, 2026 by
tonycoder-hub
Loading…
5 of 8 tasks
Ensure device agnostic for examples/docs/templates
#6770
opened Aug 17, 2026 by
kaixuanliu
Contributor
Loading…
Do not quantize the teacher by default in the distillation scripts
#6769
opened Aug 16, 2026 by
behroozazarkhalili
Collaborator
Loading…
Require liger-kernel 0.8.2 and drop the SAPO warning filter
#6768
opened Aug 15, 2026 by
albertvillanova
Member
•
Draft
2
Test one Python version on PRs, matrix nightly
#6763
opened Aug 14, 2026 by
qgallouedec
Member
Loading…
Add Weighted Instruction Tuning loss to SFTTrainer
#6747
opened Aug 14, 2026 by
C-anwoy
Loading…
5 of 8 tasks
Align the chunked-loss config access between SFT and Distillation
#6744
opened Aug 13, 2026 by
qgallouedec
Member
•
3/3
Loading…
fix(data): fix _pack_wrapped corrupting data on sliced input tables
#6733
opened Aug 13, 2026 by
AuthRan
Loading…
4 tasks done
fix(trainer): make compute_flops_per_token invariant to embedding tying
#6731
opened Aug 13, 2026 by
AuthRan
Loading…
3 tasks done
fix(models): restore state in _unwrap_model_for_generation on error
#6730
opened Aug 13, 2026 by
AuthRan
Loading…
3 tasks done
fix(trainer): restore tokenizer padding side after completion generation
#6729
opened Aug 13, 2026 by
AuthRan
Loading…
3 tasks done
fix(rewards): use rightmost delimiter in reasoning_accuracy_reward
#6728
opened Aug 13, 2026 by
AuthRan
Loading…
3 tasks done
[DistillationTrainer refactor] Support tool calling
#6723
opened Aug 12, 2026 by
qgallouedec
Member
Loading…
[GRPO + RLOO] Un-expand tool-returned images (vLLM VLM fix 2/2)
#6719
opened Aug 12, 2026 by
Strongich
Contributor
Loading…
[GRPO + RLOO] Feed vLLM unexpanded image placeholders (vLLM VLM fix 1/2)
#6718
opened Aug 12, 2026 by
Strongich
Contributor
Loading…
Previous Next
ProTip!
Follow long discussions with comments:>50.