Bert Base En Fr Es De Zh Cased

🚀 bert-base-en-fr-es-de-zh-cased

This project shares smaller versions of bert-base-multilingual-cased that support a custom number of languages, preserving the original model's accuracy.

🚀 Quick Start

We are sharing smaller versions of bert-base-multilingual-cased that handle a custom number of languages. Unlike distilbert-base-multilingual-cased, our versions give exactly the same representations produced by the original model which preserves the original accuracy.

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("Geotrend/bert-base-en-fr-es-de-zh-cased")
model = AutoModel.from_pretrained("Geotrend/bert-base-en-fr-es-de-zh-cased")

Additional Information

To generate other smaller versions of multilingual transformers please visit our Github repo.

📚 Documentation

For more information please visit our paper: Load What You Need: Smaller Versions of Multilingual BERT.

How to cite

@inproceedings{smallermbert,
  title={Load What You Need: Smaller Versions of Mutlilingual BERT},
  author={Abdaoui, Amine and Pradel, Camille and Sigel, Grégoire},
  booktitle={SustaiNLP / EMNLP},
  year={2020}
}

📄 License

The project uses the Apache-2.0 license.

📞 Contact

Please contact amine@geotrend.fr for any question, feedback or request.