conv-bert-base / README.md

Xenova HF Staff

whitphx

Add/update the quantized ONNX model files and README.md for Transformers.js v3 (#1)

b8baede verified over 1 year ago

preview code

Raw History Blame Contribute Delete

1.35 kB

---
base_model: YituTech/conv-bert-base
library_name: transformers.js
---
https://huggingface.co/YituTech/conv-bert-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:** Feature extraction w/ `Xenova/conv-bert-base`.

```javascript
import { pipeline } from '@huggingface/transformers';
// Create feature extraction pipeline
const extractor = await pipeline('feature-extraction', 'Xenova/conv-bert-base');
// Perform feature extraction
const output = await extractor('This is a test sentence.');
console.log(output)
// Tensor {
//   dims: [ 1, 8, 768 ],
//   type: 'float32',
//   data: Float32Array(6144) [ -0.13742968440055847, -0.6912388205528259, ... ],
//   size: 6144
// }
```

---

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`).

	---
	base_model: YituTech/conv-bert-base
	library_name: transformers.js
	---

	https://huggingface.co/YituTech/conv-bert-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: Feature extraction w/ `Xenova/conv-bert-base`.

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

	// Create feature extraction pipeline
	const extractor = await pipeline('feature-extraction', 'Xenova/conv-bert-base');

	// Perform feature extraction
	const output = await extractor('This is a test sentence.');
	console.log(output)
	// Tensor {
	// dims: [ 1, 8, 768 ],
	// type: 'float32',
	// data: Float32Array(6144) [ -0.13742968440055847, -0.6912388205528259, ... ],
	// size: 6144
	// }
	```

	---

	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`).