Upload model

README.md

@@ -4,72 +4,57 @@ tags:
 - xlm-roberta
 datasets:
 - UKPLab/m2qa
-- rajpurkar/squad_v2
 ---
 
-# M2QA Adapter: QA Head for MAD-X+Domain Setup
-This adapter is part of the M2QA publication to achieve language and domain transfer via adapters.  
-📃 Paper: [TODO](TODO)  
-🏗️ 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)  
+# Adapter `AdapterHub/m2qa-xlm-roberta-base-mad-x-domain-qa-head` for xlm-roberta-base
 
-**Important:** This adapter only works together with the MAD-X language adapters and the M2QA MAD-X-Domain adapters. This QA adapter was trained on the SQuAD v2 dataset.
-
-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.
+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 and includes a prediction head for question answering.
 
+This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
 
 ## Usage
 
-First, install `adapters`:
+First, install `adapter-transformers`:
 
 ```
-pip install -U adapters
+pip install -U adapter-transformers
 ```
+_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 adapters import AutoAdapterModel
-from adapters.composition import Stack
+from transformers import AutoAdapterModel
 
 model = AutoAdapterModel.from_pretrained("xlm-roberta-base")
-
-# 1. Load language adapter
-language_adapter_name = model.load_adapter("de/wiki@ukp") # MAD-X+Domain uses the MAD-X language adapter
-
-# 2. Load domain adapter
-domain_adapter_name = model.load_adapter("AdapterHub/m2qa-xlm-roberta-base-mad-x-domain-news")
-
-# 3. Load QA head adapter
-qa_adapter_name = model.load_adapter("AdapterHub/m2qa-xlm-roberta-base-mad-x-domain-qa-head")
-
-# 4. Activate them via the adapter stack
-model.active_adapters = Stack(language_adapter_name, domain_adapter_name, qa_adapter_name)
+adapter_name = model.load_adapter("AdapterHub/m2qa-xlm-roberta-base-mad-x-domain-qa-head", source="hf", set_active=True)
 ```
 
+## Architecture & Training
+
 
 See our repository for more information: See https://github.com/UKPLab/m2qa/tree/main/Experiments/mad-x-domain
 
 
-## Contact
-Leon Engländer:
-- [HuggingFace Profile](https://huggingface.co/lenglaender)
-- [GitHub](https://github.com/lenglaender)
-- [Twitter](https://x.com/LeonEnglaender)
+## Evaluation results
+
+<!-- Add some description here -->
 
 ## Citation
 
+
 ```
 @article{englaender-etal-2024-m2qa,
     title="M2QA: Multi-domain Multilingual Question Answering",
-    author={Engl{"a}nder, Leon and
+    author={Engl{\"a}nder, Leon and
         Sterz, Hannah and
         Poth, Clifton and
         Pfeiffer, Jonas and
         Kuznetsov, Ilia and
         Gurevych, Iryna},
     journal={arXiv preprint},
-    url={TODO}
+    url="https://arxiv.org/abs/2407.01091",
+    month = jul,
     year="2024"
 }
 ```