---
language:
- "lzh"
tags:
- "classical chinese"
- "literary chinese"
- "ancient chinese"
- "masked-lm"
base_model: KoichiYasuoka/modernbert-small-classical-chinese-traditional
license: "apache-2.0"
pipeline_tag: "fill-mask"
mask_token: "[MASK]"
widget:
- text: "孟子[MASK]梁惠王"
---

# modernbert-small-classical-chinese

## Model Description

This is a ModernBERT model pre-trained on [Kanripo](https://www.kanripo.org) texts. Character-embeddings are enhanced into traditional/simplified characters. You can fine-tune `modernbert-small-classical-chinese` for downstream tasks, such as sentence-segmentation, POS-tagging, [dependency-parsing](https://huggingface.co/KoichiYasuoka/modernbert-small-classical-chinese-ud-embeds), and so on.

## How to Use

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