metadata

language:
  - lzh
tags:
  - classical chinese
  - literary chinese
  - ancient chinese
  - token-classification
  - pos
  - dependency-parsing
datasets:
  - universal_dependencies
license: apache-2.0
pipeline_tag: token-classification
widget:
  - text: 子曰學而時習之不亦説乎有朋自遠方來不亦樂乎人不知而不慍不亦君子乎

Xunzi-Qwen1.5-7B-upos

Model Description

This is a Qwen1.5 model pre-trained on Classical Chinese texts for POS-tagging, derived from Xunzi-Qwen1.5-7B. Every word is tagged by UPOS (Universal Part-Of-Speech) and FEATS.

How to Use

from transformers import pipeline
nlp=pipeline("upos","KoichiYasuoka/Xunzi-Qwen1.5-7B-upos",trust_remote_code=True,aggregation_strategy="simple")
print(nlp("不入虎穴不得虎子"))

Reference

安岡孝一: GPT系モデルの系列ラベリングによる品詞付与, 東洋学へのコンピュータ利用, 第38回研究セミナー (2024年7月26日), pp.3-10.