
Sign up to save your podcasts
Or
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.
Join the discussion
Changelog++ members save 3 minutes on this episode because they made the ads disappear. Join today!
Sponsors:
Featuring:
Show Notes:
Something missing or broken? PRs welcome!
4.4
2929 ratings
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.
Join the discussion
Changelog++ members save 3 minutes on this episode because they made the ads disappear. Join today!
Sponsors:
Featuring:
Show Notes:
Something missing or broken? PRs welcome!
377 Listeners
272 Listeners
284 Listeners
40 Listeners
590 Listeners
621 Listeners
215 Listeners
987 Listeners
189 Listeners
181 Listeners
192 Listeners
62 Listeners
47 Listeners
75 Listeners
53 Listeners