---
title: README
emoji: 📈
colorFrom: green
colorTo: pink
sdk: static
pinned: false
---


<p align="center">
<img style="vertical-align:middle" src="https://raw.githubusercontent.com/Adapter-Hub/adapters/main/docs/img/adapter-bert.png" width="80" />
</p>
<h1 align="center">
<span><i>Adapters</i></span>
</h1>

<h3 align="center">
A Unified Library for Parameter-Efficient and Modular Transfer Learning
</h3>
<h3 align="center">
    <a href="https://adapterhub.ml">💻 Website</a>
    &nbsp; • &nbsp;
    <a href="https://docs.adapterhub.ml">📚 Documentation</a>
    &nbsp; • &nbsp;
    <a href="https://arxiv.org/abs/2311.11077">📜 Paper</a>
    &nbsp; • &nbsp;
    <a href="https://github.com/Adapter-Hub/adapters/tree/main/notebooks">🧪 Notebook Tutorials</a>
</h3>

_Adapters_ is an add-on library to [HuggingFace's Transformers](https://github.com/huggingface/transformers), integrating [various adapter methods](https://docs.adapterhub.ml/overview.html) into [state-of-the-art pre-trained language models](https://docs.adapterhub.ml/model_overview.html) with minimal coding overhead for training and inference.

```
pip install adapters
```

🤗 Hub integration: https://docs.adapterhub.ml/huggingface_hub.html