README.md

metadata

language:
  - ja
tags:
  - japanese
  - masked-lm
license: cc-by-sa-4.0
pipeline_tag: fill-mask
mask_token: '[MASK]'
widget:
  - text: 日本に着いたら[MASK]を訪ねなさい。

deberta-large-japanese-unidic

Model Description

This is a DeBERTa(V2) model pre-trained on 青空文庫 texts with BertJapaneseTokenizer. You can fine-tune deberta-large-japanese-unidic 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/deberta-large-japanese-unidic")
model=AutoModelForMaskedLM.from_pretrained("KoichiYasuoka/deberta-large-japanese-unidic")

fugashi and unidic-lite are required.