Downloads · 30 days
18
21% of all-time downloads
Tokara-0.5B-ud-causal
KoichiYasuoka/Tokara-0.5B-ud-causal
Tokara-0.5B-ud-causal is a token classification model from KoichiYasuoka. Use it when you need labels on individual words, such as names. The card lists the license as apache-2.0.
This is a Qwen1.5 model pretrained for POS-tagging and dependency-parsing, derived from Tokara-0.5B-v0.1 refined for UDJapanese-GSDLUW.
All-time downloads
84
Public
Repo size
3.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.9 GB · 100%
At a glance
- Task
- Token Classification
- License
- apache-2.0
- Model type
- qwen2
- Access
- Public
- Created
- Oct 18, 2024
- Updated
- May 21, 2026
- SHA
- 2a8e4d68
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
Tokara-0.5B-ud-causal
Model Description
This is a Qwen1.5 model pretrained for POS-tagging and dependency-parsing, derived from Tokara-0.5B-v0.1 refined for UD_Japanese-GSDLUW.
How to Use
from transformers import pipeline
nlp=pipeline("universal-dependencies","KoichiYasuoka/Tokara-0.5B-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"))
Reference
安岡孝一: GPT系言語モデルによる国語研長単位係り受け解析, 人文科学とコンピュータシンポジウム「じんもんこん2024」論文集 (2024年12月), pp.83-90.
- Task
- Token Classification
- Type
- qwen2
- License
- apache-2.0
- Languages
- ja
- Created
- Oct 18, 2024
- Updated
- May 21, 2026