pythia-410m / README.md
whitphx's picture
whitphx HF Staff
Add/update the quantized ONNX model files and README.md for Transformers.js v3
fddc6d9 verified
|
raw
history blame
1.07 kB
metadata
base_model: EleutherAI/pythia-410m
library_name: transformers.js

https://huggingface.co/EleutherAI/pythia-410m 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: Text generation.

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

const generator = await pipeline('text-generation', 'Xenova/pythia-410m');
const output = await generator('Once upon a time, there was', { max_new_tokens: 10 });

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).