Multimodal Model

say it: “mul-tee-MOH-dul MOD-ul” /ˌmʌltiˈmoʊdəl ˈmɑdəl/

A model that handles text plus images, audio or documents.

What is Multimodal Model?

A multimodal model understands more than text, such as images, audio or documents, in the same conversation.

Level: Apprentice · More AI Basics terms at this level

Updated