Downloads · 30 days
49
17% of all-time downloads
KoichiYasuoka/modernbert-japanese-130m-ud-embeds
modernbert-japanese-130m-ud-embeds 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 mit.
This is a ModernBERT model pretrained for POS-tagging and dependency-parsing, derived from modernbert-ja-130m refined for UDJapanese-GSDLUW.
Downloads · 30 days
49
17% of all-time downloads
All-time downloads
292
Public
Repo size
1.6 GB
Likes
0
Public
Click a slice to open those files.
.bin530 MB · 98%
From the Hugging Face model README
This is a ModernBERT model pretrained for POS-tagging and dependency-parsing, derived from modernbert-ja-130m refined for UD_Japanese-GSDLUW.
from transformers import pipeline
nlp=pipeline("universal-dependencies","KoichiYasuoka/modernbert-japanese-130m-ud-embeds",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"))
Koichi Yasuoka: Dependency-Parsing upon ModernBERT with Upper Triangular Adjacency Matrix, IPSJ Symposium Series, Vol.2025, No.1 (December 2025), pp.153-158.