News for hackers. Stuff that matters.

A comment on Automatically Detecting Under-Trained Tokens in Large Language Models. Parent comment

Re:Automatically Detecting Under-Trained Tokens in Large Lan... by mycall on Sunday May 12, 2024 @11:28PM (#40339541)
> delete weights with hardly any data flowing through them

Isn't that the idea behind sparse networks?

[ Parent | on HN ]

There are no comments on this comment yet.