The Quanta Podcast podcast

Audio Edition: How Distillation Makes AI Models Smaller and Cheaper

0:00
8:18
Manda indietro di 15 secondi
Manda avanti di 15 secondi

Fundamental technique lets researchers use a big, expensive “teacher” model to train a “student” model for less.

The story How Distillation Makes AI Models Smaller and Cheaper first appeared on Quanta Magazine.

Altri episodi di "The Quanta Podcast"