Test Implementation of Mixture of Experts Universal Transformer on conditional MNIST generation
The main goal of this short project was to familiarize myself with expert parallel and MoE, but I also wanted to do parameter sharing for fun.
-
Notifications
You must be signed in to change notification settings - Fork 0
rishiiyer01/MoEUTmnist
About
Test Implementation of Mixture of Experts Universal Transformer on conditional MNIST generation
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published