Building foundation models may not be necessary for everyone, but organizations should at least understand how they work to remain relevant. It offers a deeper understanding of the technology. Initiating open-source models like Jamba can drive innovation and experimentation, enabling the optimization of serving and training models across different infrastructures. Transparent documentation in a technical white paper encourages technical enthusiasts to delve into the details.
First there was Mamba… now there is Jamba from AI21. This is a model that combines the best non-transformer goodness of Mamba with good ‘ol attention layers. This results in a highly performant and efficient model that AI21 has open sourced! We hear all about it (along with a variety of other LLM things) from AI21’s co-founder Yoav.
Leave us a comment
Changelog++ members save 3 minutes on this episode because they made the ads disappear. Join today!
Sponsors:
- Fly.io – The home of Changelog.com — Deploy your apps and databases close to your users. In minutes you can run your Ruby, Go, Node, Deno, Python, or Elixir app (and databases!) all over the world. No ops required. Learn more at fly.io/changelog and check out the speedrun in their docs.
- Changelog News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today.
Featuring:
Show Notes:
Something missing or broken? PRs welcome!