Add model card
#1
by
nielsr
HF Staff
- opened
README.md
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: open_clip
|
| 4 |
+
pipeline_tag: image-feature-extraction
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
# OpenVision
|
| 8 |
+
|
| 9 |
+
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).
|
| 10 |
+
|
| 11 |
+
The models provide image features and are suitable for use in multimodal systems.
|
| 12 |
+
|
| 13 |
+
Project page: https://ucsc-vlaa.github.io/OpenVision
|
| 14 |
+
Code: https://github.com/UCSC-VLAA/OpenVision.
|