News for hackers. Stuff that matters.
Re:Unlimiformer: Long-Range Transformers with Unlimited Leng... by logophobia on Friday May 05, 2023 @08:57PM (#35836917)
An alternative which I've used with some succes are structured state space models: https://srush.github.io/annotated-s4/. A very different approach that works well for quite a few types of problems.

There are no comments on this comment yet.