Adapters

A Unified Library for Parameter-Efficient and Modular Transfer Learning

๐Ÿ’ป Website   โ€ข   ๐Ÿ“š Documentation   โ€ข   ๐Ÿ“œ Paper   โ€ข   ๐Ÿงช Notebook Tutorials

Adapters is an add-on library to HuggingFace's Transformers, integrating various adapter methods into state-of-the-art pre-trained language models with minimal coding overhead for training and inference.

pip install adapters

๐Ÿค— Hub integration: https://docs.adapterhub.ml/huggingface_hub.html