Distilbert Base En Fr Es De Zh Cased

🚀 distilbert-base-en-fr-es-de-zh-cased

We are sharing smaller versions of distilbert-base-multilingual-cased that handle a custom number of languages. These versions produce the same representations as the original model, preserving its accuracy.

🚀 Quick Start

We are sharing smaller versions of distilbert-base-multilingual-cased that can handle a specific number of languages. These custom - sized models generate the exact same representations as the original one, thus maintaining the original accuracy.

For more information, you can refer to our paper: Load What You Need: Smaller Versions of Multilingual BERT.

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer, AutoModel

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

If you want to generate other smaller versions of multilingual transformers, please visit our Github repo.

How to cite

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

📚 Documentation

📄 License

This project is licensed under the Apache - 2.0 license.

Contact

Please contact amine@geotrend.fr for any questions, feedback, or requests.