metadata

language:
  - ja
tags:
  - japanese
  - token-classification
  - pos
base_model: llm-jp/llm-jp-1.3b-v1.0
datasets:
  - universal_dependencies
license: apache-2.0
pipeline_tag: token-classification
widget:
  - text: 国境の長いトンネルを抜けると雪国であった。

llm-jp-1.3b-upos

Model Description

This is a GPT-2 model for POS-tagging, derived from llm-jp-1.3b-v1.0. Every short-unit-word is tagged by UPOS (Universal Part-Of-Speech) and FEATS.

How to Use

from transformers import pipeline
nlp=pipeline("upos","KoichiYasuoka/llm-jp-1.3b-upos",trust_remote_code=True,aggregation_strategy="simple")
print(nlp("国境の長いトンネルを抜けると雪国であった。"))