README.md

metadata

language:
  - ja
tags:
  - japanese
  - masked-lm
  - wikipedia
license: cc-by-sa-3.0
pipeline_tag: fill-mask
widget:
  - text: 酸素ボンベを充[MASK]する。

bert-large-japanese-char-extended

Model Description

This is a BERT model pre-trained on Japanese Wikipedia texts, derived from bert-large-japanese-char. Character-embeddings are enhanced into 常用漢字/人名用漢字 characters. You can fine-tune bert-large-japanese-char-extended for downstream tasks, such as POS-tagging, dependency-parsing, and so on.

How to Use

from transformers import AutoTokenizer,AutoModelForMaskedLM
tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/bert-large-japanese-char-extended")
model=AutoModelForMaskedLM.from_pretrained("KoichiYasuoka/bert-large-japanese-char-extended")