---
language: de
license: mit
datasets: cc100
---

# xlm-roberta-base-focus-extend-german

XLM-R adapted to German using "FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models".

Code: https://github.com/konstantinjdobler/focus

Paper: https://arxiv.org/abs/2305.14481

## Usage
```python
from transformers import AutoTokenizer, AutoModelForMaskedLM

tokenizer = AutoTokenizer.from_pretrained("konstantindobler/xlm-roberta-base-focus-extend-german")
model = AutoModelForMaskedLM.from_pretrained("konstantindobler/xlm-roberta-base-focus-extend-german")

# Use model and tokenizer as usual
```

## Details
The model is based on [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) and was adapted to German.
The original multilingual tokenizer was extended with the top 30k tokens of a language-specific German tokenizer. The new embeddings were initialized with FOCUS.
The model was then trained on data from CC100 for 390k optimizer steps. More details and hyperparameters can be found [in the paper](https://arxiv.org/abs/2305.14481).

## Disclaimer
The web-scale dataset used for pretraining and tokenizer training (CC100) might contain personal and sensitive information.
Such behavior needs to be assessed carefully before any real-world deployment of the models.

## Citation
Please cite FOCUS as follows:

```bibtex
@misc{dobler-demelo-2023-focus,
    title={FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models},
    author={Konstantin Dobler and Gerard de Melo},
    year={2023},
    eprint={2305.14481},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}
```