# Wikipedia Pre-training

This is a BERT model specifically designed for Japanese dependency parsing, used to detect head words in long unit words, implemented in a question-answering format.

mLUKE is the multilingual extension of LUKE, supporting named entity recognition, relation classification, and question answering tasks in 24 languages

A small BERT model pre-trained on Japanese Wikipedia, optimized for financial text mining

A BERT model pre-trained on Japanese text using character-level tokenization and whole word masking techniques, suitable for Japanese natural language processing tasks.

BERT model pre-trained on Japanese text using character-level tokenization and whole word masking, trained on the Japanese Wikipedia version as of August 31, 2020

A pre-trained BERT model for Galician (12 layers, case-sensitive). Trained on Wikipedia data.

This is a Japanese BERT pre-trained model based on character-level tokenization and whole word masking techniques, requiring no dependency on `fugashi` or `unidic_lite` toolkits.

This is a lightweight version of distilbert-base-multilingual-cased, specifically optimized for Turkish while maintaining original accuracy.

A compact French version of the BERT model customized from bert-base-multilingual-cased, maintaining original accuracy

The XLM model is a cross-lingual language model pre-trained on Wikipedia texts in 100 languages using masked language modeling objectives.