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.
From "Changelog Master Feed"
Listen on your iPhone
Download our iOS app and listen to interviews anywhere. Enjoy all of the listener functions in one slick package. Why not give it a try?
Comments
Add comment Feedback