metadata

language:
  - ja
tags:
  - japanese
  - masked-lm
license: cc-by-sa-4.0
pipeline_tag: fill-mask
mask_token: '[MASK]'
widget:
  - text: 入[MASK]外無之候江戸大水又ハ大地震なと
  - text: 日[MASK]守御望之由可令披露候

roberta-small-hi-char-mlm

Model Description

This is a RoBERTa model pre-trained on HI texts with character tokenizer. This uses is_decoder=False option.

How to Use

from transformers import AutoTokenizer,AutoModelForMaskedLM
tokenizer=AutoTokenizer.from_pretrained("nakamura196/roberta-small-hi-char-mlm")
model=AutoModelForMaskedLM.from_pretrained("nakamura196/roberta-small-hi-char-mlm")