ModelListedExternal

Dino Vitb8

with ONNX weights to be compatible with Transformers.js.

Sourcehuggingface.co/Xenova/dino-vitb8/tree/975f195f7a726edf63710f1e650a8b804011578c

KindOtherBase modelfacebook/dino-vitb8VersionRevision 975f195

Model source

Kind: Other
File size: 47.4–328 MB
Base model: facebook/dino-vitb8
Version: vRevision 975f195
Updated: Sep 22, 2026
Downloads: 3.1K
Source: Hugging Face

Source description

https://huggingface.co/facebook/dino-vitb8 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-vitb8');
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 975f195f7a726edf63710f1e650a8b804011578c

huggingface.co/Xenova/dino-vitb8/tree/975f195f7a726edf63710f1e650a8b804011578c

Verified Sep 9

Model artifacts

7 artifacts

onnx/model_bnb4.onnx

onnx · 49.1 MB · SHA-256 2f9bae3af836…98d5 · Hugging Face

Download

onnx/model_fp16.onnx

onnx · 164 MB · SHA-256 493aef4b6906…6e7d · Hugging Face

Download

onnx/model_q4.onnx

onnx · 54.1 MB · SHA-256 2fdde152be2d…bb0c · Hugging Face

Download

onnx/model_q4f16.onnx

onnx · 47.4 MB · SHA-256 06bcf494b879…e3b6 · Hugging Face

Download

onnx/model_quantized.onnx

onnx · 84.7 MB · SHA-256 53137b69f107…3983 · Hugging Face

Download

onnx/model_uint8.onnx

onnx · 84.2 MB · SHA-256 ee5b9d824164…8f46 · Hugging Face

Download

onnx/model.onnx

onnx · 328 MB · SHA-256 ac14409dae88…0ecb · Hugging Face

Download

Source excerpts

2 excerpts

ReadmeSep 9huggingface.co/Xenova/dino-vitb8

--- base_model: facebook/dino-vitb8 library_name: transformers.js --- https://huggingface.co/facebook/dino-vitb8 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-vitb8'); 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-vitb8

Source context: 3096 downloads · 0 likes · Pipeline image-feature-extraction · Library transformers.js · Repo Xenova/dino-vitb8