metadata

language:
  - lzh
tags:
  - classical chinese
  - literary chinese
  - ancient chinese
license: apache-2.0
pipeline_tag: fill-mask
widget:
  - text: 孟子[MASK]梁惠王

roberta-classical-chinese-large-char

Model Description

This is a RoBERTa model pre-trained on Classical Chinese texts, derived from GuwenBERT-large. Character-embeddings are enhanced into traditional/simplified characters. You can fine-tune roberta-classical-chinese-large-char for downstream tasks, such as sentencization, POS-tagging, dependency-parsing, and so on.

How to Use

from transformers import AutoTokenizer,AutoModel
tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/roberta-classical-chinese-large-char")
model=AutoModel.from_pretrained("KoichiYasuoka/roberta-classical-chinese-large-char")