强化学习相关框架汇总
1、https://github.com/yaof20/Flash-RL
🔗 GitHub:https://github.com/yaof20/Flash-RL
🔗 Blog:https://fengyao.notion.site/flash-rl
2、verl by 字节:https://github.com/volcengine/verl
3、ROLL by 阿里:https://github.com/alibaba/ROLL
4、Slime by 智谱:https://github.com/THUDM/slime
5、TRL by Hugging Face:https://github.com/huggingface/trl
6、ART by OpenPipe AI:https://github.com/OpenPipe/ART,专for Agent的强化学习框架
7、Prime-RL by Prime Intellect:https://github.com/PRIME-RL
8、Nemo-RL by NVIDIA:https://github.com/NVIDIA-NeMo/RL
9、AReaL by Ant Research:https://github.com/inclusionAI/AReaL
10、Torchtune by PyTorch:https://github.com/pytorch/torchtune
11、Open-instruct by Allen AI:https://github.com/allenai/open-instruct
Talk is cheap. Show me the code