Webssl Dino7b Full8b 518

🚀 Web-SSL DINO ViT-7B: 8B MetaCLIP data, 518 Resolution

A 7 billion parameter Vision Transformer (ViT) trained with DINOv2 self-supervised learning on web-scale image data without language supervision.

🚀 Quick Start

Web-SSL DINO 7B is a Vision Transformer model with 7 billion parameters. It is trained using self - supervised learning on 8 billion web images without language supervision. This model shows that proper - scaled pure visual learning can match or outperform language - supervised models like CLIP in various vision tasks.

✨ Features

• High - Performance Vision Model: Demonstrates excellent performance in traditional vision benchmarks and multimodal tasks such as visual question answering and OCR & chart understanding.
• Self - Supervised Learning: Trained on a large - scale web image dataset without language supervision, highlighting the power of pure visual learning.

📦 Installation

The installation process is mainly about setting up the transformers library. You can install it via pip:

pip install transformers

💻 Usage Examples

Basic Usage

from transformers import AutoImageProcessor, Dinov2Model
import torch
from PIL import Image

processor = AutoImageProcessor.from_pretrained('facebook/webssl-dino7b-full8b-518')
model = Dinov2Model.from_pretrained('facebook/webssl-dino7b-full8b-518')

# Process an image
image = Image.open('path/to/image.jpg')
inputs = processor(images=image, return_tensors="pt")
with torch.no_grad():
    outputs = model(**inputs)
cls_features = outputs.last_hidden_state[:, 0]  # CLS token features
patch_features = outputs.last_hidden_state[:, 1:] # patch-wise token features

📚 Documentation

Model Details

Model Descriptions

Web-SSL DINO 7B is trained using self - supervised learning on 8 billion web images without language supervision. This model shows that when pure visual learning is scaled appropriately, it can match or exceed the performance of language - supervised models like CLIP in various vision tasks. It performs well in both traditional vision benchmarks and multimodal tasks including visual question answering and OCR & chart understanding.

📄 License

This project is licensed under the CC - BY - NC - 4.0 license.

📄 Citation

@article{fan2025scaling,
  title={Scaling Language-Free Visual Representation Learning}, 
  author={David Fan and Shengbang Tong and Jiachen Zhu and Koustuv Sinha and Zhuang Liu and Xinlei Chen and Michael Rabbat and Nicolas Ballas and Yann LeCun and Amir Bar and Saining Xie},
  year={2025},
  eprint={2504.01017},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}