Instructions to use UCSC-VLAA/openvision-vit-tiny-patch8-224 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- OpenCLIP
How to use UCSC-VLAA/openvision-vit-tiny-patch8-224 with OpenCLIP:
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:UCSC-VLAA/openvision-vit-tiny-patch8-224') tokenizer = open_clip.get_tokenizer('hf-hub:UCSC-VLAA/openvision-vit-tiny-patch8-224') - Notebooks
- Google Colab
- Kaggle
metadata
license: apache-2.0
library_name: open_clip
pipeline_tag: image-feature-extraction
OpenVision
This repository contains the model described in the paper OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning.
Project page: https://ucsc-vlaa.github.io/OpenVision