FreeAIRepo
Training & fine-tuning

huggingface/trl

Train transformer language models with reinforcement learning.

Really freeApache-2.0Python
Stars
20k
Forks
3.1k
Open issues
151
Last push
today

About trl

trl is a free, open-source machine learning tool by huggingface, written mainly in Python. Train transformer language models with reinforcement learning. It has 20k GitHub stars and 3.1k forks, and was last updated today. It's released under the Apache-2.0 license, a standard open-source license.

License
Apache-2.0
Language
Python
Stars
19,570
Last update
today
Runs on Mac
Not stated
GPU
Not stated
Paid API key
Not required
Self-hostable
Yes

Similar free tools

All Training & fine-tuning tools →

trl FAQ

Is trl free?

Yes. trl is open source and free to use. It's released under the Apache-2.0 license, a standard open-source license.

Does trl run on a Mac?

Its README doesn't say. Check the installation guide on GitHub before you start.

Does trl need a GPU?

Its README doesn't state hardware needs. AI models generally run much faster with a GPU.

Is trl still maintained?

Yes. It was last updated today and has 151 open issues on GitHub.

What are alternatives to trl?

Similar free, open-source tools include align-anything, pytorch-image-models, DoRA, HRM-Text.

Related topics