metadata

language:
  - ja
tags:
  - japanese
  - pos
  - dependency-parsing
base_model: abeja/gpt2-large-japanese
datasets:
  - universal_dependencies
license: mit
pipeline_tag: token-classification
widget:
  - text: 全学年にわたって小学校の国語の教科書に挿し絵が用いられている

abeja-gpt2-large-japanese-ud-causal

Model Description

This is a GPT-2 model pretrained for POS-tagging and dependency-parsing, derived from gpt2-large-japanese-upos refined for UD_Japanese-GSDLUW.

How to Use

from transformers import pipeline
nlp=pipeline("universal-dependencies","KoichiYasuoka/abeja-gpt2-large-japanese-ud-causal",trust_remote_code=True)
print(nlp("全学年にわたって小学校の国語の教科書に挿し絵が用いられている"))