lgessler/microbert-indonesian-m

This is a MicroBERT model for Indonesian.

• Its suffix is -m, which means that it was pretrained using supervision from masked language modeling.
• The unlabeled Indonesian data was taken from a June 2022 dump of Indonesian Wikipedia, downsampled to 1,439,772 tokens.
• The UD treebank UD_Indonesian-GSD, v2.10, totaling 122,021 tokens, was used for labeled data.

Please see the repository and the paper for more details.