README.md

metadata

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

modernbert-large-classical-chinese-traditional

Model Description

This is a ModernBERT model pre-trained on Kanripo texts. NVIDIA A100-SXM4-40GB×8 took 24 hours 16 minutes for training. You can fine-tune modernbert-large-classical-chinese-traditional for downstream tasks, such as sentence-segmentation, POS-tagging, dependency-parsing, and so on.

How to Use

from transformers import AutoTokenizer,AutoModelForMaskedLM
tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/modernbert-large-classical-chinese-traditional")
model=AutoModelForMaskedLM.from_pretrained("KoichiYasuoka/modernbert-large-classical-chinese-traditional")