Skip to content

Pull requests: huggingface/trl

New pull request New
75 Open 1,380 Closed
75 Open 1,380 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

Enable direct loading of LoRA adapters in vLLM to streamline GRPO/Online Dpo training
#3133 opened Mar 22, 2025 by maoulee Loading…
💎 Gemma 3 VLM SFT example script for single-image and multi-image
#3131 opened Mar 21, 2025 by sergiopaniego Loading…
5 tasks
3
improvement(utils.py): simplify repeating completion string
#3122 opened Mar 20, 2025 by tpoisonooo Loading…
4
[Research] Layer Skip SFT
#3111 opened Mar 19, 2025 by ariG23498 Loading…
11
feat: Add Interleaved Trainer implementation
#3107 opened Mar 18, 2025 by ucalyptus2 Loading…
3 tasks done
Co-Locating vLLM Instances with Training Processes Via External Launcher
#3105 opened Mar 18, 2025 by toslali-ibm Loading…
2 of 5 tasks
1
Update sft trainer to include better packing
#3100 opened Mar 17, 2025 by Ishan-Kumar2 Loading…
4 tasks done
1
Speeding up dataset packing code to use itertools.chain() instead of sum()
#3095 opened Mar 16, 2025 by max-kaufmann Loading…
@shirinyamani
add cli dict parsing for grpo_config
#3082 opened Mar 14, 2025 by Tavish9 • Draft
2 of 5 tasks
7
[GRPO] add vlm training capabilities to the trainer
#3072 opened Mar 13, 2025 by CompN3rd Loading…
3 of 5 tasks
17
Fix: Multi gpu hang for ORPO and CPO Trainer
#3069 opened Mar 13, 2025 by NanoCode012 Loading…
1 of 5 tasks
1
2
[WIP] PEFT 🤝 Liger DPO
#3065 opened Mar 12, 2025 by SalmanMohammadi • Draft
5 tasks
1
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
Fast packing and truncation
#3009 opened Mar 4, 2025 by mariosasko Loading…
3 of 5 tasks
12
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
Support ReMax Algorithm
#2955 opened Feb 25, 2025 by liziniu Loading…
3 tasks done
7
[Models] Activation checkpointing from TrorchTune
#2954 opened Feb 25, 2025 by kashif Loading…
11
Agents
#2936 opened Feb 23, 2025 by August-murr Loading…
27
Provide more accurate error messages to make the program more robust. 😴 stale No update from the author, will be closed soon
#2932 opened Feb 22, 2025 by dignfei Loading…
4 tasks
3
Add the metrics completion_length_max and completion_length_min
#2930 opened Feb 22, 2025 by dignfei Loading…
4 tasks
4
Supporting multi-vLLM inference for GRPO
#2929 opened Feb 22, 2025 by ghrua Loading…
2 of 5 tasks
11
Liger GRPO support
#2926 opened Feb 21, 2025 by SalmanMohammadi • Draft
4 tasks
2
Remove CUDA synchronization in mean_token_accuracy 😴 stale No update from the author, will be closed soon
#2902 opened Feb 19, 2025 by cyyever Loading…
1 task done
5
ProTip! Updated in the last three days: updated:>2025-03-18.