Hugging Face's logo

AdapterHub
/
m2qa-xlm-roberta-base-mad-x-domain-qa-head

Adapters
xlm-roberta
Model card Files Community
m2qa-xlm-roberta-base-mad-x-domain-qa-head / README.md
lenglaender's picture
lenglaender
Upload model
0d104cb verified
preview code
|
raw
history blame
1.67 kB
metadata
tags:
  - adapter-transformers
  - xlm-roberta
datasets:
  - UKPLab/m2qa

Adapter AdapterHub/m2qa-xlm-roberta-base-mad-x-domain-qa-head for xlm-roberta-base

An adapter for the xlm-roberta-base model that was trained on the UKPLab/m2qa dataset and includes a prediction head for question answering.

This adapter was created for usage with the adapter-transformers library.

Usage

First, install adapter-transformers:

pip install -U adapter-transformers

Note: adapter-transformers is a fork of transformers that acts as a drop-in replacement with adapter support. More

Now, the adapter can be loaded and activated like this:

from transformers import AutoAdapterModel

model = AutoAdapterModel.from_pretrained("xlm-roberta-base")
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

Evaluation results

Citation 

@article{englaender-etal-2024-m2qa,
    title="M2QA: Multi-domain Multilingual Question Answering",
    author={Engl{\"a}nder, Leon and
        Sterz, Hannah and
        Poth, Clifton and
        Pfeiffer, Jonas and
        Kuznetsov, Ilia and
        Gurevych, Iryna},
    journal={arXiv preprint},
    url="https://arxiv.org/abs/2407.01091",
    month = jul,
    year="2024"
}