Instructions to use UCSC-VLAA/openvision-vit-small-patch16-160 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UCSC-VLAA/openvision-vit-small-patch16-160 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="UCSC-VLAA/openvision-vit-small-patch16-160")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("UCSC-VLAA/openvision-vit-small-patch16-160", dtype="auto") - Notebooks
- Google Colab
- Kaggle
metadata
license: apache-2.0
library_name: transformers
pipeline_tag: image-feature-extraction
OpenVision
This repository contains the model for extracting image features as described in OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning.
More information can be found on the project page and the Github repository.