Add model card

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](https://huggingface.co/papers/2505.04601).

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

Please review and merge if everything looks good.

README.md

@@ -0,0 +1,14 @@
+---
+license: apache-2.0
+library_name: open_clip
+pipeline_tag: image-feature-extraction
+---
+
+# OpenVision
+
+This repository contains the model for the OpenVision encoder described in [OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning](https://huggingface.co/papers/2505.04601).
+
+The models provide image features and are suitable for use in multimodal systems.
+
+Project page: https://ucsc-vlaa.github.io/OpenVision
+Code: https://github.com/UCSC-VLAA/OpenVision.