Skip to content

Pull requests: huggingface/trl

New pull request New
83 Open 2,353 Closed
83 Open 2,353 Closed
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
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

fix: invalidate ZeRO-3 param coordinator trace in add_hooks
#4693 opened Dec 15, 2025 by roycho96 Loading…
1 of 5 tasks
Fix KeyError with transformers 5.0.0+ where push_to_hub_token is removed
#4691 opened Dec 14, 2025 by Manodeepray Loading…
3 tasks done
Fix typos
#4690 opened Dec 14, 2025 by qgallouedec Loading…
1
feat: DeepSeek V3.2 Off-policy sequence masking
#4689 opened Dec 13, 2025 by casinca • Draft
5 tasks
GKDTrainer: Fix return_outputs in Liger kernel path and update tests
#4688 opened Dec 13, 2025 by roycho96 Loading…
2 of 5 tasks
2
Align stable trainers
#4687 opened Dec 12, 2025 by qgallouedec Loading…
5 tasks
1
Move prepare_model_for_kbit_training, enable_gradient_checkpointing, prepare_peft_model to experimental.utils
#4686 opened Dec 12, 2025 by qgallouedec Loading…
1
Align GRPO and RLOO initialization
#4685 opened Dec 12, 2025 by qgallouedec Loading…
3
Align import utils with transformers
#4684 opened Dec 12, 2025 by qgallouedec Loading…
1
Move get_reward function to experimental.utils
#4683 opened Dec 12, 2025 by qgallouedec Loading…
5 tasks
1
loss calculation for evaluation without training
#4673 opened Dec 11, 2025 by SonuDixit Loading…
5 tasks
Update import structure
#4665 opened Dec 11, 2025 by qgallouedec • Draft
Add GRPO QLoRA free notebook
#4660 opened Dec 10, 2025 by sergiopaniego • Draft
5 tasks
[WIP] GRPO-inspired Online DPO refactor
#4659 opened Dec 10, 2025 by d-tiapkin • Draft
2 of 7 tasks
@kashif
feature: Add RTPO Trainer
#4652 opened Dec 9, 2025 by SolarWindRider Loading…
6 tasks done
5
Set version to packaged one in notebooks
#4648 opened Dec 9, 2025 by sergiopaniego Loading…
5 tasks
1
Overwrite model default generation config used by model.generate
#4647 opened Dec 9, 2025 by albertvillanova Loading…
7 of 9 tasks
17
Include generation_config for tiny model uploads
#4643 opened Dec 9, 2025 by qgallouedec Loading…
4
CPOTrainer - Incorrect handling of different length chosen/rejected p…
#4639 opened Dec 8, 2025 by davmels Loading…
Preserve truncated tokens in BFD packing
#4632 opened Dec 5, 2025 by qgallouedec Loading…
1
11
Update docs landing with latest details
#4624 opened Dec 4, 2025 by sergiopaniego Loading…
6 tasks
1
Support async reward functions and parallelize call to reward functions.
#4567 opened Nov 24, 2025 by pramodith Loading…
3 of 5 tasks
1
13
Add cross-tokenizer distillation support for GKD and MiniLLM trainers
#4561 opened Nov 22, 2025 by sambhavnoobcoder Loading…
1
Add PSPO trust region method as alternative to clipping in GRPOTrainer
#4548 opened Nov 19, 2025 by MCDwyer Loading…
2 of 5 tasks
@kashif
4
Add compute_metrics parameter for GRPOTrainer
#4534 opened Nov 17, 2025 by colinzhaoxp Loading…
3
ProTip! What’s not been updated in a month: updated:<2025-11-14.