Skip to content

Pull requests: huggingface/trl

New pull request New
79 Open 1,411 Closed
79 Open 1,411 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

😷 Fix SFT masking EOS when equal to PAD
#3200 opened Mar 31, 2025 by qgallouedec Loading…
6
Improve GRPO trainer error message for invalid num_generations
#3199 opened Mar 31, 2025 by AliBakly Loading…
Support for Models With Pre-Finetuned LoRA Adapters in GRPO: Add use_peft_as_reference Flag
#3196 opened Mar 31, 2025 by LoganVegnaSHOP Loading…
5 tasks done
1
7
[GRPO] Allow the use of the vllm logprobs, rather than recomputing them
#3193 opened Mar 31, 2025 by edbeeching Loading…
13
GRPO: Scalable training with one LLM/node
#3186 opened Mar 31, 2025 by jglaser • Draft
4 tasks
⏯️ Fix resuming from checkpoint GRPO
#3185 opened Mar 31, 2025 by qgallouedec Loading…
1
Integrate Liger GRPO Loss to GRPO Trainer
#3184 opened Mar 31, 2025 by shivam15s • Draft
1 of 5 tasks
@kashif
2
🚀 Enhance GRPO VLLM server from sync to async and accelerate training
#3182 opened Mar 30, 2025 by binary-husky Loading…
3
GRPO Overlong soft punishment based on DAPO
#3177 opened Mar 29, 2025 by 1485840691-eng • Draft
5 tasks
4
Co-Locating vLLM w/ training to achieve higher throughput and GPU utilization
#3162 opened Mar 26, 2025 by toslali-ibm Loading…
2 of 5 tasks
1
12
🏃 Faster CI
#3160 opened Mar 25, 2025 by qgallouedec Loading…
5 tasks
4
Fix: Compatibility for formatting_func returning a list
#3147 opened Mar 24, 2025 by YeFD Loading…
4 of 5 tasks
6
Fix length bias for Dr GRPO
#3138 opened Mar 23, 2025 by idoru Loading…
5 tasks
24
Extend BCO Trainer dataset format support
#3134 opened Mar 22, 2025 by reihig-ut Loading…
1 of 5 tasks
Add GRPO/ Online DPO support for quantitative models when use vllm as infer backbone.
#3133 opened Mar 22, 2025 by maoulee Loading…
4
improvement(utils.py): simplify repeating completion string
#3122 opened Mar 20, 2025 by tpoisonooo Loading…
6
feat: Add Interleaved Trainer implementation
#3107 opened Mar 18, 2025 by ucalyptus2 Loading…
3 tasks done
Update sft trainer to include better packing
#3100 opened Mar 17, 2025 by Ishan-Kumar2 Loading…
4 tasks done
1
add cli dict parsing for grpo_config
#3082 opened Mar 14, 2025 by Tavish9 Loading…
2 of 5 tasks
8
[GRPO] add vlm training capabilities to the trainer
#3072 opened Mar 13, 2025 by CompN3rd Loading…
3 of 5 tasks
24
[WIP] PEFT 🤝 Liger DPO
#3065 opened Mar 12, 2025 by SalmanMohammadi • Draft
5 tasks
2
Static cache GRPO
#3023 opened Mar 7, 2025 by qgallouedec • Draft
5 tasks
1
[WIP] Iterative training scripts for SPIN and SPPO
#3011 opened Mar 5, 2025 by jkx19 • Draft
3 of 5 tasks
Fixing GRPO reward_func being a model with DeepSpeed ZeRO-3
#2984 opened Feb 28, 2025 by jamesbraza Loading…
4
Feature: Add SGLang as inference backend for generation in GRPO
#2981 opened Feb 28, 2025 by jhinpan Loading…
5 tasks done
30
ProTip! What’s not been updated in a month: updated:<2025-03-01.