2min chapter

The Data Exchange with Ben Lorica cover image

Efficient Methods for Natural Language Processing

The Data Exchange with Ben Lorica

CHAPTER

The Challenge of Fine Tuning GPUs

The goal usually is for the fine tuning step, hopefully you can get by with CPU's even. It depends on how large your model is, I mean, whether it can fit in memory and how much operation they need to do. The major challenge of fine tuning is can we get the good few short results that we see with huge models on much smaller models? We're seeing a GPD-3 doing wonderfully with only a handful of examples but smaller models still need quite a bit of them.

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