Latent Space: The AI Engineer Podcast cover image

Llama 2: The New Open LLM SOTA (ft. Nathan Lambert, Matt Bornstein, Anton Troynikov, Russell Kaplan, Whole Mars Catalog et al.)

Latent Space: The AI Engineer Podcast

00:00

Open-Source Models and Benchmarking

This chapter explores the excitement around open-source models and their implications for retrieval-augmented generation, emphasizing the necessity for realistic benchmarks aligned with practical applications. The discussion includes collaborations on community-sourced benchmarks, the capabilities of Llama 2, and the potential for fine-tuning models to enhance performance in various tasks.

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