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 regularly 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:
- Colab notebook tutorials, a series notebooks providing an introduction to all the main concepts of (adapter-)transformers and AdapterHub
- 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:
@inproceedings{pfeiffer2020AdapterHub,
title={AdapterHub: A Framework for Adapting Transformers},
author={Pfeiffer, Jonas and
R{\"u}ckl{\'e}, Andreas and
Poth, Clifton and
Kamath, Aishwarya and
Vuli{\'c}, Ivan and
Ruder, Sebastian and
Cho, Kyunghyun and
Gurevych, Iryna},
booktitle={Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations},
pages={46--54},
year={2020}
}