Open Models Almanac
Methodsmodel architecturemultimodal architecture

single mention · model architecture

Dedicated multimodal encoders before the LLM

Processes multimodal data with dedicated encoders before passing representations to the language model.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See multimodal architecture for the methods filed beside it.

Filed under model architecture › multimodal architecture