issues
search
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
Update train.py
#55
Closed
KnightBits
closed
1 year ago
KnightBits
commented
1 year ago
Added autosave of model state every 5 thousand iterations
Added autosave of model state every 5 thousand iterations