ModelListedExternal

Dino Vits16

with ONNX weights to be compatible with Transformers.js.

Sourcehuggingface.co/Xenova/dino-vits16/tree/517e3f80ee1d5d063ca5306afa66863e28848869

KindOtherBase modelfacebook/dino-vits16VersionRevision 517e3f8

Model source

Kind: Other
File size: 12.4–82.9 MB
Base model: facebook/dino-vits16
Version: vRevision 517e3f8
Updated: Sep 21, 2026
Downloads: 8.6K
Source: Hugging Face

Source description

https://huggingface.co/facebook/dino-vits16 with ONNX weights to be compatible with Transformers.js.

Usage (Transformers.js)

If you haven't already, you can install the Transformers.js JavaScript library from NPM using:

npm i @huggingface/transformers

Example: Perform image feature extraction.

import { pipeline } from '@huggingface/transformers';

const image_feature_extractor = await pipeline('image-feature-extraction', 'Xenova/dino-vits16');
const url = 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/cats.png';
const features = await image_feature_extractor(url);

Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).

Sources

1 source

Hugging FacePrimaryVersion 517e3f80ee1d5d063ca5306afa66863e28848869

huggingface.co/Xenova/dino-vits16/tree/517e3f80ee1d5d063ca5306afa66863e28848869

Verified Sep 9

Model artifacts

7 artifacts

onnx/model_bnb4.onnx

onnx · 13.2 MB · SHA-256 820ae635d6d1…4d2e · Hugging Face

Download

onnx/model_fp16.onnx

onnx · 41.6 MB · SHA-256 383754e89c18…4cef · Hugging Face

Download

onnx/model_q4.onnx

onnx · 14.5 MB · SHA-256 9845fca37b28…19e3 · Hugging Face

Download

onnx/model_q4f16.onnx

onnx · 12.4 MB · SHA-256 694ff2316e5d…e4ed · Hugging Face

Download

onnx/model_quantized.onnx

onnx · 21.6 MB · SHA-256 686df030e42d…172a · Hugging Face

Download

onnx/model_uint8.onnx

onnx · 21.3 MB · SHA-256 72815a8ce7d9…4eda · Hugging Face

Download

onnx/model.onnx

onnx · 82.9 MB · SHA-256 34a4816b8715…3f30 · Hugging Face

Download

Source excerpts

2 excerpts

ReadmeSep 9huggingface.co/Xenova/dino-vits16

--- base_model: facebook/dino-vits16 library_name: transformers.js --- https://huggingface.co/facebook/dino-vits16 with ONNX weights to be compatible with Transformers.js. ## Usage (Transformers.js) If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using: ```bash npm i @huggingface/transformers ``` **Example:** Perform image feature extraction. ```js import { pipeline } from '@huggingface/transformers'; const image_feature_extractor = await pipeline('image-feature-extraction', 'Xenova/dino-vits16'); const url = 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/cats.png'; const features = await image_feature_extractor(url); ``` Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).

NoteSep 9huggingface.co/Xenova/dino-vits16

Source context: 8595 downloads · 0 likes · Pipeline image-feature-extraction · Library transformers.js · Repo Xenova/dino-vits16