# Self-supervised visual representation

This is a 3-billion parameter vision Transformer model trained on 2 billion web images through DINOv2 self-supervised learning, capable of learning powerful visual representations without language supervision.

A 224-resolution Vision Transformer model based on 2 billion MetaCLIP data, trained using DINOv2 self-supervised learning method

A 3-billion parameter Vision Transformer model trained using DINOv2 self-supervised learning on lightly filtered web-scale image data, without language supervision.

A 3-billion parameter vision Transformer model trained on 2 billion carefully curated MetaCLIP data using DINOv2 self-supervised learning framework