Instructions to use webgpu/Phi-4-mini-instruct-ONNX-GQA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use webgpu/Phi-4-mini-instruct-ONNX-GQA with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('text-generation', 'webgpu/Phi-4-mini-instruct-ONNX-GQA');
Download tokenizer.json from webgpu/Phi-4-mini-instruct-ONNX-GQA: direct link, hf CLI and curl.
- Browser
- Download file 13.3 MB
-
https://huggingface.co/webgpu/Phi-4-mini-instruct-ONNX-GQA/resolve/main/tokenizer.json
- Command line
-
hf download hf://webgpu/Phi-4-mini-instruct-ONNX-GQA/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/webgpu/Phi-4-mini-instruct-ONNX-GQA/resolve/main/tokenizer.json
13.3 MB
- Xet hash:
- 0ac277ce5c07fe6065eeadc14b2fee7fea37588b981648fc76745d12add96061
- Size of remote file:
- 13.3 MB
- SHA256:
- b5ee8c0b1f9862ab7052a99edd2f8f3e69258b2d2670c5880bb44d3fc0599c4c
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.