generated from fastai/nbdev_template
-
Notifications
You must be signed in to change notification settings - Fork 1.8k
Pull requests: huggingface/trl
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[GRPO] Decouple gradient accumulation from the number of minibatches generated
#3388
opened Apr 29, 2025 by
edbeeching
Loading…
[SFT] Handle
formatting_func + completion_only_loss
#3385
opened Apr 29, 2025 by
LeonEricsson
Loading…
3 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
[GRPO] adds experimental support for the SSR replay buffer
#3325
opened Apr 18, 2025 by
edbeeching
•
Draft
[vllm] support base_url parameter for vLLM client initialization
#3324
opened Apr 18, 2025 by
re-imagined
Loading…
Allow for saving the PPOTrainer value model (critic model)
#3308
opened Apr 16, 2025 by
AMindToThink
Loading…
[DPO] Model forward pass padding side fix
#3307
opened Apr 16, 2025 by
LeonEricsson
Loading…
2 of 5 tasks
PPO value_model can't be None, so it shouldn't be Optional
#3300
opened Apr 15, 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
[NOT MEANT TO BE MERGED] Log correct/incorrect lengths
#3263
opened Apr 8, 2025 by
qgallouedec
•
Draft
Previous Next
ProTip!
Type g p on any issue or pull request to go back to the pull request listing page.