issues
search
karpathy
/
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
MIT License
37.55k
stars
5.99k
forks
source link
Implement muP and add code for mup guide blog
#549
Closed
ndey96
closed
2 months ago
ndey96
commented
2 months ago
TODOS
[x] Implement muP
[ ] coordinate check
[ ] muTransfer LR
[ ] proxy model tuning
TODOS