https://huggingface.co/YituTech/conv-bert-medium-small 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 @xenova/transformers
Example: Feature extraction w/ Xenova/conv-bert-medium-small
.
import { pipeline } from '@xenova/transformers';
// Create feature extraction pipeline
const extractor = await pipeline('feature-extraction', 'Xenova/conv-bert-medium-small', { quantized: false });
// Perform feature extraction
const output = await extractor('This is a test sentence.');
console.log(output)
// Tensor {
// dims: [ 1, 8, 384 ],
// type: 'float32',
// data: Float32Array(3072) [ 0.5316754579544067, 0.5101212859153748, ... ],
// size: 3072
// }
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
).
- Downloads last month
- 6
Inference API (serverless) does not yet support transformers.js models for this pipeline type.