generated from fastai/nbdev_template
-
Notifications
You must be signed in to change notification settings - Fork 1.9k
Pull requests: huggingface/trl
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[GRPO] Pad per minibatch instead of per generation batch
#3495
opened May 26, 2025 by
edbeeching
•
Draft
3 tasks
feat(grpo): validate gradient_accumulation_steps vs steps_per_generation for on-policy GRPO
#3493
opened May 25, 2025 by
HarryHsing
Loading…
Allow an user to train from a local dataset
#3470
opened May 19, 2025 by
gogo2464
Loading…
1 of 5 tasks
Add async tool-enabled vLLM server for GRPO training via OpenAI-compatible interface
#3469
opened May 19, 2025 by
BjarniHaukur
Loading…
5 tasks
[SFT] add warning if dataset's input_ids exceed max_length
#3449
opened May 15, 2025 by
HERIUN
Loading…
1 of 5 tasks
🛠️ quantization support for vllm generation
#3428
opened May 8, 2025 by
shirinyamani
Loading…
5 tasks
Fix GRPO/DAPO/Dr.GRPO documentation: formula corrections and KL divergence clarification
#3395
opened Apr 30, 2025 by
JenWei0312
Loading…
1 of 5 tasks
Reintroduce
generate method for PPOTrainer
#3374
opened Apr 27, 2025 by
CloseChoice
Loading…
4 tasks done
add support for reward func using nn.Module in GRPOTrainer
#3372
opened Apr 27, 2025 by
Tavish9
Loading…
1 of 5 tasks
[Feat] Suppport SGLang as rollout engine of GRPO trainer
#3370
opened Apr 27, 2025 by
ryang-max
Loading…
2 of 8 tasks
Allow for saving the PPOTrainer value model (critic model)
#3308
opened Apr 16, 2025 by
AMindToThink
Loading…
Modified GRPOTrainer to accumulate gradient within a single training batch
#3288
opened Apr 13, 2025 by
jarrelscy
Loading…
3 of 5 tasks
Previous Next
ProTip!
Filter pull requests by the default branch with base:main.