Open Models Almanac
Methodsmodel architecturemultimodal architecture

single mention · model architecture

Pixtral-style variable-resolution vision encoder

Uses a Pixtral-style vision encoder designed to handle variable image sizes and aspect ratios.

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