SmolVLA
Hugging Facewe do not use tiling. We use the global image only, in addition to a pixel shuffle operation, limiting the visual tokens to 64 per frame.
1 more from this model
Using fewer visual tokens
specific method · filed under model architecture
Reduces visual-token count, in one described implementation by using a global image and pixel shuffle without tiling.
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 Reduce the number of visual tokens, Using fewer visual tokens, using a minimal number of visual tokens.
2 quotes from 2 sources, one card per model, each opening with its strongest.
we do not use tiling. We use the global image only, in addition to a pixel shuffle operation, limiting the visual tokens to 64 per frame.
Using fewer visual tokens