Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models.
Samira Abnar, Harshay Shah, Dan Busbridge, Alaaeldin El-Nouby, Joshua M. Susskind, Vimal Thilak
Browse the full ICML paper archive.
Samira Abnar, Harshay Shah, Dan Busbridge, Alaaeldin El-Nouby, Joshua M. Susskind, Vimal Thilak
Browse the full ICML paper archive.