---
base_model: facebook/hiera-base-224-in1k-hf
library_name: transformers.js
---

https://huggingface.co/facebook/hiera-base-224-in1k-hf 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 classification with `onnx-community/hiera-base-224-in1k-hf`
```js
import { pipeline } from '@huggingface/transformers';

// Create an image classification pipeline
const classifier = await pipeline('image-classification', 'onnx-community/hiera-base-224-in1k-hf');

// Classify an image
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/tiger.jpg';
const output = await classifier(url);
console.log(output);
// [
//   { label: 'tiger, Panthera tigris', score: 0.759323239326477 },
//   { label: 'tiger cat', score: 0.08907650411128998 },
//   { label: 'lynx, catamount', score: 0.0008640264859423041 },
//   { label: 'jaguar, panther, Panthera onca, Felis onca', score: 0.0007982379174791276 },
//   { label: 'leopard, Panthera pardus', score: 0.00041627752943895757 }
// ]
```

---

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`).