ModelListedExternal

Openvision Vit Huge Patch14 84

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.

Sourcehuggingface.co/UCSC-VLAA/openvision-vit-huge-patch14-84/tree/b36d2b9534f9c68de2434cc65f13b63f912081fa

KindOtherVersionRevision b36d2b9

Model source

Kind: Other
File size: 3.61 GB
Version: vRevision b36d2b9
Updated: Sep 22, 2026
Downloads: 0
Source: Hugging Face

Source description

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.

Sources

1 source

Hugging FacePrimaryVersion b36d2b9534f9c68de2434cc65f13b63f912081fa

huggingface.co/UCSC-VLAA/openvision-vit-huge-patch14-84/tree/b36d2b9534f9c68de2434cc65f13b63f912081fa

Verified Sep 9

Model artifacts

1 artifact

open_clip_pytorch_model.bin

bin · 3.61 GB · SHA-256 6fdf2f22513a…337a · Hugging Face

Download

Source excerpts

2 excerpts

ReadmeSep 9huggingface.co/UCSC-VLAA/openvision-vit-huge-patch14-84

--- 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](https://huggingface.co/papers/2505.04601). Project Page: [https://ucsc-vlaa.github.io/OpenVision/](https://ucsc-vlaa.github.io/OpenVision/) For details on training and usage, please refer to the [Github repository](https://github.com/UCSC-VLAA/OpenVision).

NoteSep 9huggingface.co/UCSC-VLAA/openvision-vit-huge-patch14-84

Source context: 0 downloads · 0 likes · Pipeline image-feature-extraction · Library transformers · Repo UCSC-VLAA/openvision-vit-huge-patch14-84