# WordPiece Tokenization

CamemBERTv2 is a French language model pre-trained on a 275 billion-word French text corpus, serving as the second-generation version of CamemBERT. It adopts the RoBERTa architecture with optimized tokenizer and training data.

A LUKE model improved from Japanese BERT, specifically optimized for Japanese named entity recognition tasks

A BERT base model pretrained on Indonesian Wikipedia using Masked Language Modeling (MLM) objective, case insensitive.

This is a BERT-based Indonesian pretrained model trained on Wikipedia and newspaper data, suitable for various natural language processing tasks.