←back to thread

Zebra-Llama – Towards efficient hybrid models

(arxiv.org)
111 points mirrir | 1 comments | 06 Dec 25 20:15 UTC | HN request time: 0.251s | source
1. Reubend ◴[06 Dec 25 22:35 UTC] No.46177206[source]▶
It would be REALLY cool to see this same technique applied to a much more recent OSS model distillation. For example, Mistral 3 14B would be a great target. How efficient can we get inference there?