huggingface/exporters
Converts Hugging Face transformer models to Core ML and TFLite formats for deployment on mobile and edge devices.
Not currently ranked — collecting fresh signals.
star history
Exporters is a conversion tool that transforms Hugging Face Transformers models (originally in PyTorch, TensorFlow, or JAX) into Core ML format suitable for iOS/mobile deployment. It wraps coremltools to provide a more convenient interface integrated with the Transformers library and Hugging Face Hub. For TFLite conversions, the project redirects users to the Optimum library instead.
Frequently asked
- What is huggingface/exporters?
- Converts Hugging Face transformer models to Core ML and TFLite formats for deployment on mobile and edge devices.
- Is exporters open source?
- Yes — huggingface/exporters is open source, released under the Apache-2.0 license.
- What language is exporters written in?
- huggingface/exporters is primarily written in Python.
- How popular is exporters?
- huggingface/exporters has 698 stars on GitHub.
- Where can I find exporters?
- huggingface/exporters is on GitHub at https://github.com/huggingface/exporters.