Xenova/fastvit_sa24.apple_in1k
By Xenova · ↓ 6 · ♥ 0 · Updated 2025-06-27
What's in this repo
This page lists the files in Xenova/fastvit_sa24.apple_in1k, including model.onnx, model_bnb4.onnx, model_fp16.onnx and more.
- 8 ONNX models (.onnx files)
- 14 files, including 8 .onnx, 3 .json, 1 .md
- Repository size ~361 MB
- Last updated 2025-06-27
ONNX files
| File | Size | Download |
|---|---|---|
| onnx/model.onnx | 82.4 MB | Download |
| onnx/model_bnb4.onnx | 68.7 MB | Download |
| onnx/model_fp16.onnx | 41.4 MB | Download |
| onnx/model_int8.onnx | 21.4 MB | Download |
| onnx/model_q4.onnx | 68.9 MB | Download |
| onnx/model_q4f16.onnx | 35.6 MB | Download |
| onnx/model_quantized.onnx | 21.4 MB | Download |
| onnx/model_uint8.onnx | 21.4 MB | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
https://huggingface.co/timm/fastvit_sa24.apple_in1k 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: Perform image classification with Xenova/fastvit_sa24.apple_in1k.
import { pipeline } from '@huggingface/transformers';
// Create an image classification pipeline
const classifier = await pipeline('image-classification', 'Xenova/fastvit_sa24.apple_in1k');
// Classify an image
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/tiger.jpg';
const output = await classifier(url, { top_k: 5 });
console.log(output);
// [
// { label: 'tiger, Panthera tigris', score: 0.5324224829673767 },
// { label: 'tiger cat', score: 0.18026751279830933 },
// { label: 'lynx, catamount', score: 0.0019241739064455032 },
// { label: 'jaguar, panther, Panthera onca, Felis onca', score: 0.0018087428761646152 },
// { label: 'tabby, tabby cat', score: 0.0017144557787105441 }
// ]
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).
Model info
Created: 2024-05-09
Updated: 2025-06-27
View on Hugging Face