huggingface/trl

Train transformer language models with reinforcement learning.

[view on github]last commit: Oct 20, 2026

stars

19,557

7d

+50

30d

+212

90d

+675

## star history

## found in

Awesome Open Source AI/🛠️ 7. Training & Fine-tuning Ecosystem Awesome local LLM/Training and Fine-tuning