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
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Encoder-Decoder
#6
Bachstelze
closed
1 year ago
39
GPU requirements
#5
ejarkm
closed
1 year ago
3
Unified reward function/model architecture for a wide range of tasks
#4
James4Ever0
opened
1 year ago
2
Add wandb logging
#3
ell-hol
opened
1 year ago
2
Add HF's Accelerate
#2
ell-hol
closed
1 year ago
4
Easier (and faster) chunk and inplace under nograd
#1
hypnopump
closed
1 year ago
1
Previous