Add model card

This PR adds a model card by 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).

README.md

@@ -0,0 +1,13 @@
+---
+license: apache-2.0
+pipeline_tag: image-feature-extraction
+library_name: transformers
+---
+
+# OpenVision
+
+This repository contains the OpenVision model described in the paper [OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning](https://huggingface.co/papers/2505.04601).
+
+Project page: https://ucsc-vlaa.github.io/OpenVision
+
+Code: https://github.com/UCSC-VLAA/OpenVision