hiyouga / EasyR1
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
Why this job: says: training framework; topics: reinforcement-learning
What it does
This project is a clean fork of the original veRL project to support vision language models, we thank all the authors for providing such a high-performance RL training framework.
Get started
git clone https://github.com/hiyouga/EasyR1.git
cd EasyR1
pip install -e . You need: Python 3.9+; transformers>=4.54.0; flash-attn>=2.4.3
- Maintenance
- Active
- Last commit 2 days ago
- Stars
- 5,213
- +5 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.3.2
- Released 13 months ago
- Built with
- Python
- 99% of the code
Is it looked after?
- Contributors
- 3
- Last 90 days
- Issues
- 84% closed
- 59 still open
- Pull requests
- 230 merged
- 15 waiting
- Releases
- 3
- 0 in the last year
- Contributing guide (opens in new tab)
- No security policy
- Code of conduct (opens in new tab)
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| R6410418 / Jackrong-llm-finetuning-guide | 1,732 | 7 days ago | Apache-2.0 | No downloads |
| lasgroup / SDPO | 1,143 | 4 months ago | Apache-2.0 | No downloads |
| Goekdeniz-Guelmez / MLX-LoRA-Studio | 289 | 14 days ago | MIT | Mac |
More: languages, topics and project record
Languages
- Python 99%
- Dockerfile 1%
- Makefile <1%
Topics
- ai
- gpt
- llm
- nlp
- reinforcement-learning
- rl
- deepseek
- qwen
Project record
- JobFine-tuning
- StatusListed
- Commits219
- Forks399
- Watching22
- Stars in 28 days+29
- CreatedFeb 22, 2025
- First seen by usNov 7, 2026
- CheckedNov 9, 2026