News for hackers. Stuff that matters.

A comment on Ferret: A Multimodal Large Language Model by Apple. Parent comment

Re:Ferret: A Multimodal Large Language Model by Apple by dilippkumar on Sunday December 24, 2023 @12:35AM (#38751390)
Some of the modalities in multimodal are non-linguistic. For example, image or video input. In those cases, is it still a language model?
[ Parent | on HN ]
Re:Ferret: A Multimodal Large Language Model by Apple by bbor on Sunday December 24, 2023 @01:38PM (#38755524)
I’d say yeah cause it’s understanding the inputs through linguistic structures/patterns
[ Parent | on HN ]