ModelListedExternal

Openvision Vit Large Patch14 84

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

Sourcehuggingface.co/UCSC-VLAA/openvision-vit-large-patch14-84/tree/d3d2927557795e18f89bde5de07e3a08a6d9ee7c

KindOtherVersionRevision d3d2927

Model source

Kind: Other
File size: 1.54 GB
Version: vRevision d3d2927
Updated: Sep 21, 2026
Downloads: 0
Source: Hugging Face

Source description

This repository contains the model weights for the OpenVision ViT 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/ Code: https://github.com/UCSC-VLAA/OpenVision

Sources

1 source

Hugging FacePrimaryVersion d3d2927557795e18f89bde5de07e3a08a6d9ee7c

huggingface.co/UCSC-VLAA/openvision-vit-large-patch14-84/tree/d3d2927557795e18f89bde5de07e3a08a6d9ee7c

Verified Sep 9

Model artifacts

1 artifact

open_clip_pytorch_model.bin

bin · 1.54 GB · SHA-256 2b6c2702d212…aa42 · Hugging Face

Download

Source excerpts

2 excerpts

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

--- license: apache-2.0 library_name: transformers pipeline_tag: image-feature-extraction --- This repository contains the model weights for the OpenVision ViT model described in the paper [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/ Code: https://github.com/UCSC-VLAA/OpenVision

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

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