TRL is Hugging Face's library for post-training and aligning language models with supervised fine-tuning, DPO and reinforcement learning methods like PPO.
From the README
pip install git+https://github.com/huggingface/trl.git
Excerpts from the project README on GitHub. Copyright and licensing remain with the respective authors.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeTrain transformer language models with reinforcement learning.
trl has 19.2k stars on GitHub. It has been forked 2.9k times. trl is written mainly in Python. It has been in active development since 2020. trl is available under the Apache-2.0 license.
Read the full guideWhat is trl?
Train transformer language models with reinforcement learning.
Is trl open source?
trl is an open-source project. It is released under the Apache-2.0 license.
Is trl free?
Yes. trl is free and open source — you can use, modify and self-host it.
What license does trl use?
trl is available under the Apache-2.0 license.
What language is trl written in?
trl is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/huggingface-trl.html)
