Re:Minimal implementation of Mamba, the new LLM architecture...
by esafak on Wednesday December 20, 2023 @04:35PM
(#38713953)
Everybody doesn't know Mamba. You can't stay on top of everything in ML so stop trying. Since you asked, Mamba is a neural architecture based on structured state space models (SSMs) that aims to replace Transformers. For me right now just know that counts as staying on top of things. If I need to know more than that I can have the computer summarize it for me.
[ Parent
| on HN ]
There are no comments on this comment yet.