Instructions to use onnx-community/embeddinggemma-300m-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use onnx-community/embeddinggemma-300m-ONNX with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('sentence-similarity', 'onnx-community/embeddinggemma-300m-ONNX');
transformers.js v4
#24
by fosple - opened
@Xenova Now that transformers.js v4 Preview is out (πππ) would be awesome to export https://huggingface.co/google/embeddinggemma-300m-qat-q8_0-unquantized as onnx q8 and https://huggingface.co/google/embeddinggemma-300m-qat-q4_0-unquantized as q4 for transformers.js v4 βΊοΈ