Upload model

README.md

@@ -6,43 +6,58 @@ datasets:
 - UKPLab/m2qa
 ---
 
-# Adapter `AdapterHub/m2qa-xlm-roberta-base-mad-x-2-creative-writing` for xlm-roberta-base
+# M2QA Adapter: Domain Adapter for MAD-X² Setup
+This adapter is part of the M2QA publication to achieve language and domain transfer via adapters.  
+📃 Paper: [https://arxiv.org/abs/2407.01091](https://arxiv.org/abs/2407.01091)  
+🏗️ GitHub repo: [https://github.com/UKPLab/m2qa](https://github.com/UKPLab/m2qa)  
+💾 Hugging Face Dataset: [https://huggingface.co/UKPLab/m2qa](https://huggingface.co/UKPLab/m2qa)  
 
-An [adapter](https://adapterhub.ml) for the `xlm-roberta-base` model that was trained on the [UKPLab/m2qa](https://huggingface.co/datasets/UKPLab/m2qa/) dataset.
+**Important:** This adapter only works together with the MAD-X-2 language and QA head adapter.
+
+This [adapter](https://adapterhub.ml) for the `xlm-roberta-base` model that was trained using the **[Adapters](https://github.com/Adapter-Hub/adapters)** library. For detailed training details see our paper or GitHub repository: [https://github.com/UKPLab/m2qa](https://github.com/UKPLab/m2qa). You can find the evaluation results for this adapter on the M2QA dataset in the GitHub repo and in the paper.
 
-This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
 
 ## Usage
 
-First, install `adapter-transformers`:
+First, install `adapters`:
 
 ```
-pip install -U adapter-transformers
+pip install -U adapters
 ```
-_Note: adapter-transformers is a fork of transformers that acts as a drop-in replacement with adapter support. [More](https://docs.adapterhub.ml/installation.html)_
 
 Now, the adapter can be loaded and activated like this:
 
 ```python
-from transformers import AutoAdapterModel
+from adapters import AutoAdapterModel
+from adapters.composition import Stack
 
 model = AutoAdapterModel.from_pretrained("xlm-roberta-base")
-adapter_name = model.load_adapter("AdapterHub/m2qa-xlm-roberta-base-mad-x-2-creative-writing", source="hf", set_active=True)
-```
 
-## Architecture & Training
+# 1. Load language adapter
+language_adapter_name = model.load_adapter("AdapterHub/m2qa-xlm-roberta-base-mad-x-2-english") 
 
+# 2. Load domain adapter
+domain_adapter_name = model.load_adapter("AdapterHub/m2qa-xlm-roberta-base-mad-x-2-creative-writing")
+
+# 3. Load QA head adapter
+qa_adapter_name = model.load_adapter("AdapterHub/m2qa-xlm-roberta-base-mad-x-2-qa-head")
+
+# 4. Activate them via the adapter stack
+model.active_adapters = Stack(language_adapter_name, domain_adapter_name, qa_adapter_name)
+```
 
-See our repository for more information: See https://github.com/UKPLab/m2qa/tree/main/Experiments/mad-x-2
 
+See our repository for more information: See https://github.com/UKPLab/m2qa/tree/main/Experiments/mad-x-2
 
-## Evaluation results
 
-<!-- Add some description here -->
+## Contact
+Leon Engländer:
+- [HuggingFace Profile](https://huggingface.co/lenglaender)
+- [GitHub](https://github.com/lenglaender)
+- [Twitter](https://x.com/LeonEnglaender)
 
 ## Citation
 
-
 ```
 @article{englaender-etal-2024-m2qa,
     title="M2QA: Multi-domain Multilingual Question Answering",