huggingface/exporters
Export Hugging Face models to Core ML and TensorFlow Lite
This tool helps machine learning engineers and mobile developers integrate advanced AI models into Apple applications. It takes pre-trained models from the Hugging Face ecosystem (in PyTorch or TensorFlow) and converts them into the Core ML format. The output is a Core ML model file ready for use in iOS, macOS, or watchOS apps, enabling on-device inference.
690 stars. No commits in the last 6 months.
Use this if you need to deploy a complex Hugging Face Transformer model directly onto Apple devices for fast, localized AI inference.
Not ideal if your target deployment environment is not an Apple device or if you primarily work with TensorFlow Lite models.
Stars
690
Forks
52
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 23, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/huggingface/exporters"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
apple/coremltools
Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.
hollance/YOLO-CoreML-MPSNNGraph
Tiny YOLO for iOS implemented using CoreML but also using the new MPS graph API.
tensorflow/swift-apis
Swift for TensorFlow Deep Learning Library
hollance/Forge
A neural network toolkit for Metal
hanleyweng/CoreML-in-ARKit
Simple project to detect objects and display 3D labels above them in AR. This serves as a basic...