This model works fine, you can download and try to run it, but I'm currently too lazy to write a README.
The fast vision encoder (FastViTHD) used in this model is not really that much faster (as tested in their paper) than a SoViT-400m 14-384 on RKNPU2 :D

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support