Xenova's picture
Xenova HF Staff
Add/update the quantized ONNX model files and README.md for Transformers.js v3 (#1)
5aee1ee verified
metadata
base_model: hf-tiny-model-private/tiny-random-RoFormerForQuestionAnswering
library_name: transformers.js

https://huggingface.co/hf-tiny-model-private/tiny-random-RoFormerForQuestionAnswering 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: Run question answering.

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

const answerer = await pipeline('question-answering', 'Xenova/tiny-random-RoFormerForQuestionAnswering');
const question = 'Who was Jim Henson?';
const context = 'Jim Henson was a nice puppet.';
const output = await answerer(question, context);

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 馃 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).