There’s now a Python library for RLHF called TRLX!
(The same reinforcement learning strategy used in training ChatGPT)
It works well with Hugging Face models, supports multiple RL strategies, and requires very little code!
(The same reinforcement learning strategy used in training ChatGPT)
It works well with Hugging Face models, supports multiple RL strategies, and requires very little code!
Check out the repo here: github.com
Thanks to the wonderful folks with CarperAI!
Thanks to the wonderful folks with CarperAI!
Loading suggestions...