Open Models Almanac
Methodsmodel architecturemultimodal architecture

single mention · model architecture

Pretrained vision-language encoder

Uses a pretrained VLM encoder for the main vision-language stream.

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.

Also called pretrained VLM encoder.

Filed under model architecture › multimodal architecture