Name: vit small patch14 dinov2.lvd142m
Author: timm

Overview

The ViT-Small Patch14 (DINOv2) is a lightweight vision transformer pre-trained on a massive, curated dataset of 142 million images. Unlike standard supervised models, this backbone leverages self-supervised learning to extract high-quality, dense visual features without requiring labeled data. For developers, this means a powerful feature extractor that excels at semantic segmentation, image retrieval, and depth estimation with significantly lower computational overhead than larger ViT variants. It integrates seamlessly via the timm library, making it an ideal choice for building efficient downstream computer vision pipelines where latency and memory footprints are critical constraints.

Highlights

Self-supervised features optimized for dense visual tasks
Low-latency inference via small-scale ViT architecture
Easy integration through the timm library
High-performance image feature extraction without labels
Apache-2.0 license for flexible commercial deployment

Usage

Install

# Install Hugging Face transformers
pip install transformers torch

SDK Usage

# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("timm/vit_small_patch14_dinov2.lvd142m")
tokenizer = AutoTokenizer.from_pretrained("timm/vit_small_patch14_dinov2.lvd142m")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance

pip install -U huggingface_hub

CLI Download

Download the full repository

huggingface-cli download timm/vit_small_patch14_dinov2.lvd142m

Download a single file to a local folder (e.g. config.json into ./dir)

huggingface-cli download timm/vit_small_patch14_dinov2.lvd142m config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('timm/vit_small_patch14_dinov2.lvd142m')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://huggingface.co/timm/vit_small_patch14_dinov2.lvd142m

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/timm/vit_small_patch14_dinov2.lvd142m

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

pip install -U transformers torch

Load the model and run inference

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('timm/vit_small_patch14_dinov2.lvd142m')
tokenizer = AutoTokenizer.from_pretrained('timm/vit_small_patch14_dinov2.lvd142m')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance

pip install modelscope

CLI Download

Download the full repository

modelscope download --model timm/vit_small_patch14_dinov2.lvd142m

Download a single file to a local folder (e.g. README.md into ./dir)

modelscope download --model timm/vit_small_patch14_dinov2.lvd142m README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('timm/vit_small_patch14_dinov2.lvd142m')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://www.modelscope.cn/timm/vit_small_patch14_dinov2.lvd142m.git

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/timm/vit_small_patch14_dinov2.lvd142m.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook Quickstart

Install the ModelScope library

pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Load the model and run inference

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'timm/vit_small_patch14_dinov2.lvd142m')

Full Documentation

来源: HuggingFace

---
license: apache-2.0
library_name: timm
tags:

image-feature-extraction

timm

transformers

---

Model card for vit_small_patch14_dinov2.lvd142m

A Vision Transformer (ViT) image feature model. Pretrained on LVD-142M with self-supervised DINOv2 method.

Model Details

Model Type: Image classification / feature backbone

Model Stats:

- Params (M): 22.1 - GMACs: 46.8 - Activations (M): 198.8 - Image size: 518 x 518

Papers:

- DINOv2: Learning Robust Visual Features without Supervision: https://arxiv.org/abs/2304.07193 - An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2

Original: https://github.com/facebookresearch/dinov2

Pretrain Dataset: LVD-142M

Model Usage

Image Classification

python

from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model('vit_small_patch14_dinov2.lvd142m', pretrained=True)
model = model.eval()
get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1
top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)

Image Embeddings

python

from urllib.request import urlopen
from PIL import Image
import timm
img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))
model = timm.create_model(
    'vit_small_patch14_dinov2.lvd142m',
    pretrained=True,
    num_classes=0,  # remove classifier nn.Linear
)
model = model.eval()
get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)
output = model(transforms(img).unsqueeze(0))  # output is (batch_size, num_features) shaped tensor
or equivalently (without needing to set num_classes=0)
output = model.forward_features(transforms(img).unsqueeze(0))
output is unpooled, a (1, 1370, 384) shaped tensor

output = model.forward_head(output, pre_logits=True)
output is a (1, num_features) shaped tensor

Model Comparison

Explore the dataset and runtime metrics of this model in timm model results.

Citation

bibtex

@misc{oquab2023dinov2,
  title={DINOv2: Learning Robust Visual Features without Supervision},
  author={Oquab, Maxime and Darcet, Timothée and Moutakanni, Theo and Vo, Huy V. and Szafraniec, Marc and Khalidov, Vasil and Fernandez, Pierre and Haziza, Daniel and Massa, Francisco and El-Nouby, Alaaeldin and Howes, Russell and Huang, Po-Yao and Xu, Hu and Sharma, Vasu and Li, Shang-Wen and Galuba, Wojciech and Rabbat, Mike and Assran, Mido and Ballas, Nicolas and Synnaeve, Gabriel and Misra, Ishan and Jegou, Herve and Mairal, Julien and Labatut, Patrick and Joulin, Armand and Bojanowski, Piotr},
  journal={arXiv:2304.07193},
  year={2023}
}

bibtex

@article{dosovitskiy2020vit,
  title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
  author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and  Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
  journal={ICLR},
  year={2021}
}

bibtex

@misc{rw2019timm,
  author = {Ross Wightman},
  title = {PyTorch Image Models},
  year = {2019},
  publisher = {GitHub},
  journal = {GitHub repository},
  doi = {10.5281/zenodo.4414861},
  howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}