<?xml version="1.0" encoding="US-ASCII"?>
<dblp>
<article key="journals/corr/abs-2501-12370" publtype="informal" mdate="2025-02-25">
<author>Samira Abnar</author>
<author>Harshay Shah</author>
<author>Dan Busbridge</author>
<author>Alaaeldin Mohamed Elnouby Ali</author>
<author>Joshua M. Susskind</author>
<author>Vimal Thilak</author>
<title>Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models.</title>
<year>2025</year>
<month>January</month>
<volume>abs/2501.12370</volume>
<journal>CoRR</journal>
<ee type="oa">https://doi.org/10.48550/arXiv.2501.12370</ee>
<url>db/journals/corr/corr2501.html#abs-2501-12370</url>
<stream>streams/journals/corr</stream>
</article>
</dblp>
