Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
mrm8488 
posted an update May 8
Post
5523
Working on a concept GPT-2 (small) that uses KANs instead of MLPs.
The ckpt and training code will be soon on the hub.

very interested in this

Can you share what the training speeds look like ?

·

Sure

Im curious how this will turn out!

Still not yet out?