Deep Papers cover image

Llama 2: Open Foundation and Fine-Tuned Chat Models

Deep Papers

00:00

The Safety of Pre Training Models

Pre trained and fine to know lems, generally perform better than existing open source models. And then there's a number of measures they've taken to talk about the, the safety of these specific models. They go to a lot of detail about data gathering. One thing that I thought was really interesting was they go into a little bit about scrubbing PII but I also thought it was fascinating that they care to look at demographic representation in the pre training data.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app