Deprecated: The each() function is deprecated. This message will be suppressed on further calls in /home/zhenxiangba/zhenxiangba.com/public_html/phproxy-improved-master/index.php on line 456
@mrm8488 on Hugging Face: "Working on a concept `GPT-2 (small)` that uses `KANs` instead of `MLPs`. The…"
[go: Go Back, main page]
Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
mrm8488 
posted an update May 8, 2024
Post
9490
Working on a concept GPT-2 (small) that uses KANs instead of MLPs.
The ckpt and training code will be soon on the hub.
DrHouseFan-315

very interested in this
MohamedRashad

Can you share what the training speeds look like ?

·
mrm8488

Sure

dillfrescott

Im curious how this will turn out!
Arlendious

Still not yet out?

In this post