Open Models Almanac
Methodsmodel architecturemultimodal architecture

single mention · model architecture

Index-token marking for multi-image inputs

Prefixes each image's visual tokens with an index token before concatenating images.

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