---
language:
  - zh
thumbnail: https://ckip.iis.sinica.edu.tw/files/ckip_logo.png
tags:
  - pytorch
  - lm-head
  - bert
  - zh
license: gpl-3.0
---

# CKIP BERT Base Han Chinese

Pretrained model on Ancient Chinese language using a masked language modeling (MLM) objective.

## Homepage
* [ckiplab/han-transformers](https://github.com/ckiplab/han-transformers)

## Training Datasets
The copyright of the datasets belongs to the Institute of Linguistics, Academia Sinica.
* [中央研究院上古漢語標記語料庫](http://lingcorpus.iis.sinica.edu.tw/cgi-bin/kiwi/akiwi/kiwi.sh)
* [中央研究院中古漢語語料庫](http://lingcorpus.iis.sinica.edu.tw/cgi-bin/kiwi/dkiwi/kiwi.sh)
* [中央研究院近代漢語語料庫](http://lingcorpus.iis.sinica.edu.tw/cgi-bin/kiwi/pkiwi/kiwi.sh)
* [中央研究院現代漢語語料庫](http://asbc.iis.sinica.edu.tw)

## Contributors
* Chin-Tung Lin at [CKIP](https://ckip.iis.sinica.edu.tw)

## Usage

* Using our model in your script
    ```python
    from transformers import (
      AutoTokenizer,
      AutoModel,
    )

    tokenizer = AutoTokenizer.from_pretrained("ckiplab/bert-base-han-chinese")
    model = AutoModel.from_pretrained("ckiplab/bert-base-han-chinese")
    ```

* Using our model for inference
    ```python
    >>> from transformers import pipeline
    >>> unmasker = pipeline('fill-mask', model='ckiplab/bert-base-han-chinese')
    >>> unmasker("黎[MASK]於變時雍。")

    [{'sequence': '黎 民 於 變 時 雍 。',
    'score': 0.14885780215263367,
    'token': 3696,
    'token_str': '民'},
    {'sequence': '黎 庶 於 變 時 雍 。',
    'score': 0.0859643816947937,
    'token': 2433,
    'token_str': '庶'},
    {'sequence': '黎 氏 於 變 時 雍 。',
    'score': 0.027848130092024803,
    'token': 3694,
    'token_str': '氏'},
    {'sequence': '黎 人 於 變 時 雍 。',
    'score': 0.023678112775087357,
    'token': 782,
    'token_str': '人'},
    {'sequence': '黎 生 於 變 時 雍 。',
    'score': 0.018718384206295013,
    'token': 4495,
    'token_str': '生'}]
    ```