PodcastIntel
Sign in Get Started Free
Latent Space: The AI Engineer Podcast
Latent Space: The AI Engineer Podcast

MPT-7B and The Beginning of Context=Infinity — with Jonathan Frankle and Abhinav Venigalla of MosaicML

May 20, 2023 · 1h 6m
AI Summary
  • MosaicML's MPT-7B achieved SOTA in open-source with 84,000 token context length (vs GPT-3's 4,000), trained on 1 trillion tokens matching LLaMA-7B quality
  • Extended context enables new applications without requiring retrieval augmentation, representing breakthrough for commercially licensed open models
  • Context-as-infinity paradigm shift moving from limited token windows to practical document-length processing within single model pass

More from Latent Space: The AI Engineer Podcast

View all episodes →

Get AI Summaries for Every New Episode

Subscribe to Latent Space: The AI Engineer Podcast and get AI summaries, guest tracking, and email digests delivered automatically.

Sign Up Free →