Saltar al contenido

ModelPublicadoExterno

Openvision Vit Huge Patch14 224

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

Fuentehuggingface.co/UCSC-VLAA/openvision-vit-huge-patch14-224/tree/74fae5c66b294403d2fc3826fe9ad46b9bfdf689

TipoOtherVersiónRevision 74fae5c

Fuente del modelo

Tipo: Other
Tamaño del archivo: 3,61 GB
Versión: vRevision 74fae5c
Actualizado: 21 sept 2026
Descargas: 9
Fuente: Hugging Face

Descripción de la fuente

This repository contains the model described in 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

Fuentes

1 fuente

Hugging FacePrincipalVersión 74fae5c66b294403d2fc3826fe9ad46b9bfdf689

huggingface.co/UCSC-VLAA/openvision-vit-huge-patch14-224/tree/74fae5c66b294403d2fc3826fe9ad46b9bfdf689

Verificado 9 sept

Artefactos del modelo

1 artefacto

open_clip_pytorch_model.bin

bin · 3,61 GB · SHA-256 1f68ef78f00d…f704 · Hugging Face

Extractos de fuentes

2 extractos

Readme9 septhuggingface.co/UCSC-VLAA/openvision-vit-huge-patch14-224

--- pipeline_tag: image-feature-extraction library_name: open_clip license: apache-2.0 --- This repository contains the model 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 Code: https://github.com/UCSC-VLAA/OpenVision

Note9 septhuggingface.co/UCSC-VLAA/openvision-vit-huge-patch14-224

Source context: 9 downloads · 2 likes · Pipeline image-feature-extraction · Library open_clip · Repo UCSC-VLAA/openvision-vit-huge-patch14-224