README.md

metadata

language:
  - de
license: cc-by-4.0
tags:
  - question-answering
  - pytorch
  - qa
  - de
datasets: deepset/germanquad
task_categories:
  - question-answering

SVALabs - InfoXLM German QA

In this repository we present our german question answering model.

The trained model is based on InfoXLM-large and was finetuned using the SQuAD dataset and the GermanQuAD dataset.

Model Details

	Description or Link
Base model	InfoXLM-large
Finetuning task	Question Answering
Source datasets	SQuAD; GermanQuAD

Performance

The model was tested on 1692 samples of the GermanQuAD test dataset (the other samples were used for validation)

F1-Score: 89.05

EM: 74.76