Instructions to use onnx-community/BEN2-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use onnx-community/BEN2-ONNX with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('image-segmentation', 'onnx-community/BEN2-ONNX');
int8 onnx model
#5
by sunseeker001 - opened
Is there a int8 quantized model? Not just compress the weights, but also compress the activation layer.
Thanks.