ModelPublicadoExterno

Dinov2 Base

with ONNX weights to be compatible with Transformers.js.

Fuentehuggingface.co/Xenova/dinov2-base/tree/d623d125a29e343851bcedff293fdc8b6bda292b

TipoOtherModelo basefacebook/dinov2-baseVersiónRevision d623d12

Fuente del modelo

Tipo: Other
Tamaño del archivo: 47,2–331 MB
Modelo base: facebook/dinov2-base
Versión: vRevision d623d12
Actualizado: 22 sept 2026
Descargas: 1,3 mil
Fuente: Hugging Face

Descripción de la fuente

https://huggingface.co/facebook/dinov2-base 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/dinov2-base');
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).

Fuentes

1 fuente

Hugging FacePrincipalVersión d623d125a29e343851bcedff293fdc8b6bda292b

huggingface.co/Xenova/dinov2-base/tree/d623d125a29e343851bcedff293fdc8b6bda292b

Verificado 9 sept

Artefactos del modelo

7 artefactos

onnx/model_bnb4.onnx

onnx · 48,8 MB · SHA-256 8b6c42d8f642…9e3b · Hugging Face

Descargar

onnx/model_fp16.onnx

onnx · 165 MB · SHA-256 c04656628344…7da5 · Hugging Face

Descargar

onnx/model_q4.onnx

onnx · 53,8 MB · SHA-256 19f697cf7cdd…6018 · Hugging Face

Descargar

onnx/model_q4f16.onnx

onnx · 47,2 MB · SHA-256 86d3711c68b1…17f4 · Hugging Face

Descargar

onnx/model_quantized.onnx

onnx · 86,8 MB · SHA-256 1a1210212e3d…bf9c · Hugging Face

Descargar

onnx/model_uint8.onnx

onnx · 83,0 MB · SHA-256 14cb8a8ec2fb…0d1a · Hugging Face

Descargar

onnx/model.onnx

onnx · 331 MB · SHA-256 de9c675d214f…4d98 · Hugging Face

Descargar

Extractos de fuentes

2 extractos

Readme9 septhuggingface.co/Xenova/dinov2-base

--- base_model: facebook/dinov2-base library_name: transformers.js --- https://huggingface.co/facebook/dinov2-base 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/dinov2-base'); 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`).

Note9 septhuggingface.co/Xenova/dinov2-base

Source context: 1264 downloads · 0 likes · Pipeline image-feature-extraction · Library transformers.js · Repo Xenova/dinov2-base