The Quanta Podcast
Audio Edition: How Distillation Makes AI Models Smaller and Cheaper
May 14 · 8 min · 12.0 MB
0:00-8:18
Streams straight from the publisher. podnod never proxies or re-hosts episode audio.
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.
How Distillation Makes AI Models Smaller and Cheaper
quantamagazine.org