How to Scale Models for Inference

One thing we've used d is something called inference triage, a primer where you kind of use a smaller model to um gate keep like you're your larger model. That can save you a a lot of time and cost. M the second thing that makes m l ops challenging for n l p is just, it's really hard to do data augmentation in a way that's like actually semantically valid and automated.

Transcript

Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!

Get the app