Open Models Almanac
Methodsmodel architecturemultimodal architecture

single mention · model architecture

Routing image and language tokens to the VLM backbone

Routes images and language prompts to the pretrained VLM backbone.

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