Instructions to use Xenova/vit-base-patch16-224 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use Xenova/vit-base-patch16-224 with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('image-classification', 'Xenova/vit-base-patch16-224');
Creation of the model_quantized.onnx file from pytorch model
#1
by mrsarthakgupta - opened
Hi, I'm trying to create a repository identical to this one for deploying my model through transformersjs. But I could figure out how to obtain the model_quantized.onnx file from the optimum model conversion library. Please let me know how I could get that.