adapter-transformers is an extension of Huggingface's Transformers library, integrating adapters into state-of-the-art language models by incorporating AdapterHub, a central repository for pre-trained adapter modules.

This library can be used as a drop-in replacement for Huggingface Transformers and regulary synchronizes new upstream changes.

adapter-transformers currently supports Python 3.6+ and PyTorch 1.1.0+. After installing PyTorch, you can install adapter-transformers from PyPI ...

pip install -U adapter-transformers

... or from source by cloning the repository:

git clone https://github.com/adapter-hub/adapter-transformers.git
cd adapter-transformers
pip install .

HuggingFace's great documentation on getting started with Transformers can be found here. adapter-transformers is fully compatible with Transformers.

To get started with adapters, refer to these locations:

• https://docs.adapterhub.ml, our documentation on training and using adapters with adapter-transformers
• https://adapterhub.ml to explore available pre-trained adapter modules and share your own adapters
• Examples folder of this repository containing HuggingFace's example training scripts, many adapted for training adapters

If you find this library useful, please cite our paper AdapterHub: A Framework for Adapting Transformers:

@article{pfeiffer2020AdapterHub,
    title={AdapterHub: A Framework for Adapting Transformers},
    author={Jonas Pfeiffer and
            Andreas R\"uckl\'{e} and
            Clifton Poth and
            Aishwarya Kamath and
            Ivan Vuli\'{c} and
            Sebastian Ruder and
            Kyunghyun Cho and
            Iryna Gurevych},
    journal={arXiv preprint},
    year={2020},
    url={https://arxiv.org/abs/2007.07779}
}