ModelListadosExterno

Owlv2 Base Patch16

with ONNX weights to be compatible with Transformers.js.

Fontehuggingface.co/Xenova/owlv2-base-patch16/tree/7463883add9ec3fbcdfc5493010f5908313d7d32

TipoOtherModelo basegoogle/owlv2-base-patch16VersãoRevision 7463883Bnota

Fonte do modelo

Tipo: Other
Tamanho do arquivo: 122–586 MB
Modelo base: google/owlv2-base-patch16
Versão: vRevision 7463883
Atualizado: 10 de out. de 2026
Downloads: 131
Fonte: Hugging Face

Descrição da fonte

https://huggingface.co/google/owlv2-base-patch16 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: Zero-shot object detection.

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

const detector = await pipeline('zero-shot-object-detection', 'Xenova/owlv2-base-patch16');
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/astronaut.png';
const candidate_labels = ['human face', 'rocket', 'helmet', 'american flag'];
const output = await detector(url, candidate_labels);

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).

Fontes

1 fonte

Hugging FacePrimárioVersão 7463883add9ec3fbcdfc5493010f5908313d7d32

huggingface.co/Xenova/owlv2-base-patch16/tree/7463883add9ec3fbcdfc5493010f5908313d7d32

Verificado 10 de out.

Download files

Artefatos de modelo

7 artefatos

onnx/model_bnb4.onnx

onnx · 178 MB · SHA-256 efe781a31796…33b6 · Hugging Face

Download file

onnx/model_fp16.onnx

onnx · 294 MB · SHA-256 8b121655bc69…9ce9 · Hugging Face

Download file

onnx/model_q4.onnx

onnx · 185 MB · SHA-256 ec94b439bdde…e22f · Hugging Face

Download file

onnx/model_q4f16.onnx

onnx · 122 MB · SHA-256 e64ac3bfd889…1205 · Hugging Face

Download file

onnx/model_quantized.onnx

onnx · 148 MB · SHA-256 279a4827037e…1167 · Hugging Face

Download file

onnx/model_uint8.onnx

onnx · 156 MB · SHA-256 8a6a909756a0…437d · Hugging Face

Download file

onnx/model.onnx

onnx · 586 MB · SHA-256 26875cf596cd…3438 · Hugging Face

Download file

Trechos de fonte

3 trechos

Readme1 de ago.huggingface.co/Xenova/owlv2-base-patch16

--- base_model: google/owlv2-base-patch16 library_name: transformers.js --- https://huggingface.co/google/owlv2-base-patch16 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:** Zero-shot object detection. ```js import { pipeline } from '@huggingface/transformers'; const detector = await pipeline('zero-shot-object-detection', 'Xenova/owlv2-base-patch16'); const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/astronaut.png'; const candidate_labels = ['human face', 'rocket', 'helmet', 'american flag']; const output = await detector(url, candidate_labels); ``` 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`).

Note10 de out.huggingface.co/Xenova/owlv2-base-patch16

Source context: 131 downloads · 0 likes · Pipeline zero-shot-object-detection · Library transformers.js · Repo Xenova/owlv2-base-patch16

Note1 de ago.huggingface.co/Xenova/owlv2-base-patch16

Source context: 48 downloads · 0 likes · Pipeline zero-shot-object-detection · Library transformers.js · Repo Xenova/owlv2-base-patch16