Edit model card

BERT base (cased) model trained on a subset of 125M tokens of cc100-Swahili for our work Scaling Laws for BERT in Low-Resource Settings at ACL2023 Findings.

The model has 124M parameters (12L), and a vocab size of 50K. It was trained for 500K steps with a sequence length of 512 tokens and batch-size of 256.


bert-base-sw bert-medium-sw Flair mBERT SwahBERT
NERC 92.09 91.63 92.04 91.17 88.60
Topic 93.07 92.88 91.83 91.52 90.90
Sentiment 79.04 77.07 73.60 69.17 71.12
QNLI 63.34 63.87 52.82 63.48 64.72


Gorka Urbizu [1], Iñaki San Vicente [1], Xabier Saralegi [1], Rodrigo Agerri [2] and Aitor Soroa [2]

Affiliation of the authors:

[1] Orai NLP Technologies

[2] HiTZ Center - Ixa, University of the Basque Country UPV/EHU


The model is licensed under the Creative Commons Attribution 4.0. International License (CC BY 4.0).

To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.


If you use this model please cite the following paper:

  • G. Urbizu, I. San Vicente, X. Saralegi, R. Agerri, A. Soroa. Scaling Laws for BERT in Low-Resource Settings. Findings of the Association for Computational Linguistics: ACL 2023. July, 2023. Toronto, Canada

Contact information

Gorka Urbizu, Iñaki San Vicente: {g.urbizu,i.sanvicente}@orai.eus

Downloads last month

Collection including orai-nlp/bert-base-sw