huggingface

huggingface/trl

steady

Train transformer language models with reinforcement learning.

Python View on GitHub

Stars

18,720

Forks

2,807

Open issues

297

24h

+11

+0.1%

7d

+69

+0.4%

Refresh

1h

Star history (7 days)

Last checked

51m ago

Last pushed

4h ago

Next check

just now