Add model card
Browse filesThis PR adds a model card to document the OpenVision model, including links to the paper, project page, and code repository.
README.md
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: image-feature-extraction
|
| 3 |
+
library_name: transformers
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
This repository contains the OpenVision model, a fully-open and cost-effective family of advanced vision encoders for multimodal learning, as described in the paper [OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning](https://huggingface.co/papers/2505.04601).
|
| 8 |
+
|
| 9 |
+
Project Page: https://ucsc-vlaa.github.io/OpenVision/
|
| 10 |
+
|
| 11 |
+
Code: https://github.com/UCSC-VLAA/OpenVision
|