4min chapter

Towards Data Science cover image

120. Liam Fedus and Barrett Zoph - AI scaling with mixture of expert models

Towards Data Science

CHAPTER

How Many Experts Are We Talking About?

We basically only want one expert most of the time. For most of our recent work, we had like 64 or less experts. We've acta also seem to be beneficial even if you only have two experts. You don't actually really even need a super computer to get the benefits from something like this as well. So it almost makes you think of dense models aslike one end of a continuum of a mixture of experts model really.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode