Xianhang's picture
Add model card (#1)
b36d2b9 verified
metadata
license: apache-2.0
library_name: transformers
pipeline_tag: image-feature-extraction

This repository contains the model weights based on the work described in OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning.

Project Page: https://ucsc-vlaa.github.io/OpenVision/

For details on training and usage, please refer to the Github repository.