Adapters for the paper "M2QA: Multi-domain Multilingual Question Answering".
We evaluate 2 setups: MAD-X+Domain and MAD-X²
AdapterHub
university
AI & ML interests
Parameter-Efficient Fine-Tuning
Recent Activity
View all activity
Organization Card
Adapters
A Unified Library for Parameter-Efficient and Modular Transfer Learning
💻 Website • 📚 Documentation • 📜 Paper • 🧪 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
🤗 Hub integration: https://docs.adapterhub.ml/huggingface_hub.html
models
505
AdapterHub/m2qa-xlm-roberta-base-mad-x-domain-wiki
Updated
•
7
AdapterHub/m2qa-xlm-roberta-base-mad-x-domain-news
Updated
•
5
AdapterHub/m2qa-xlm-roberta-base-mad-x-2-english
Updated
•
9
AdapterHub/m2qa-xlm-roberta-base-mad-x-2-chinese
Updated
•
6
AdapterHub/m2qa-xlm-roberta-base-mad-x-2-wiki
Updated
•
9
AdapterHub/m2qa-xlm-roberta-base-mad-x-2-news
Updated
•
6
AdapterHub/m2qa-xlm-roberta-base-mad-x-domain-product-reviews
Updated
•
2
AdapterHub/m2qa-xlm-roberta-base-mad-x-2-product-reviews
Updated
•
6
AdapterHub/m2qa-xlm-roberta-base-mad-x-2-creative-writing
Updated
•
7
AdapterHub/m2qa-xlm-roberta-base-mad-x-2-turkish
Updated
•
7
datasets
None public yet