TRL
作者： huggingface
Train transformer language models with reinforcement learning: SFT, DPO, PPO, and GRPO.
星数
19,688
派生数
3,124
语言
Python
分类
Training & Fine-tuning
获取代码
# 克隆仓库git clone https://github.com/huggingface/trl
常见问题
TRL 是什么？
Train transformer language models with reinforcement learning: SFT, DPO, PPO, and GRPO.
TRL 使用安全吗？
TRL 是 huggingface 在 GitHub 上的开源项目。在生产环境使用前请先审阅源代码与许可证。
如何开始使用 TRL？
git clone https://github.com/huggingface/trl
TRL 是用什么语言写的？
openSource.faqWhatLanguageAnswer
相关项目
Unsloth
unslothaiFine-tune and run LLMs and diffusion models 2x faster with far less memory.
79.2k7.4k
LLaMA-Factory
hiyougaUnified efficient fine-tuning of 100+ LLMs and VLMs with a no-code web UI.
75.9k9.4k
DeepSpeed
microsoftDeep learning optimization library that makes distributed training and inference easy and efficient.
43.3k5.1k