lucidrains / PaLM-rlhf-pytorch

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
MIT License
7.67k stars 668 forks source link

Is it possible to train this ai using open-assistant or vice versa? #33

Closed qwertystars closed 1 year ago

qwertystars commented 1 year ago

Theoretically is it possible for an ai to train another ai?

lucidrains commented 1 year ago

@qwertystars AI is just a mathematical procedure

yea, you can mix and match components of different libraries, if you understand the procedure