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.

This model handles the following languages: english, french, spanish, german, chinese, arabic, russian, portuguese, italian, and urdu. It produces the same representations as bert-base-multilingual-cased while being 22.5% smaller in size.

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

How to use

from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("Geotrend/bert-base-10lang-cased")
model = AutoModel.from_pretrained("Geotrend/bert-base-10lang-cased")

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

How to cite

  title={Load What You Need: Smaller Versions of Multilingual BERT},
  author={Abdaoui, Amine and Pradel, Camille and Sigel, Grégoire},
  booktitle={SustaiNLP / EMNLP},


Please contact for any question, feedback or request.


Select AutoNLP in the “Train” menu to fine-tune this model automatically.

Downloads last month
Hosted inference API
Mask token: [MASK]
This model can be loaded on the Inference API on-demand.