11 citations · 24 across the 6 of their papers we have counts for
1 paper · 1 filter
Reyhan Kevser Keser, Aydin Ayanzadeh, Omid Abdollahi Aghdam +3
One of the most efficient methods for model compression is hint distillation, where the student model is injected with information (hints) from several different layers of the teac…