UCSC-VLAA

/

openvision-vit-base-patch16-384

like 1

Follow

UCSC-VLAA 85

This PR adds a model card for the OpenVision model, linking it to the paper OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning.

It also adds a relevant pipeline tag and the OpenCLIP library as library_name.

Please review and merge if everything looks good.