Adapterhub: A Framework For Adapting Transformers

Pfeiffer Jonas, Rücklé Andreas, Poth Clifton, Kamath Aishwarya, Vulić Ivan, Ruder Sebastian, Cho Kyunghyun, Gurevych Iryna. Arxiv 2020

[Paper]    
BERT Fine Tuning Model Architecture Pretraining Methods Reinforcement Learning Tools Training Techniques Transformer

The current modus operandi in NLP involves downloading and fine-tuning pre-trained models consisting of millions or billions of parameters. Storing and sharing such large trained models is expensive, slow, and time-consuming, which impedes progress towards more general and versatile NLP methods that learn from and for many tasks. Adapters – small learnt bottleneck layers inserted within each layer of a pre-trained model – ameliorate this issue by avoiding full fine-tuning of the entire model. However, sharing and integrating adapter layers is not straightforward. We propose AdapterHub, a framework that allows dynamic “stitching-in” of pre-trained adapters for different tasks and languages. The framework, built on top of the popular HuggingFace Transformers library, enables extremely easy and quick adaptations of state-of-the-art pre-trained models (e.g., BERT, RoBERTa, XLM-R) across tasks and languages. Downloading, sharing, and training adapters is as seamless as possible using minimal changes to the training scripts and a specialized infrastructure. Our framework enables scalable and easy access to sharing of task-specific models, particularly in low-resource scenarios. AdapterHub includes all recent adapter architectures and can be found at https://AdapterHub.ml.

Similar Work