Downloads · 30 days
45
18% of all-time downloads
KoichiYasuoka/modernbert-large-japanese-char-luw-upos
modernbert-large-japanese-char-luw-upos 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 ModernBERT model pre-trained on Japanese Wikipedia and 青空文庫 texts for POS-tagging and dependency-parsing, derived from modernbert-large-japanese-char. Every long-unit-word is tagged by UPOS (Universal Part-O…
Downloads · 30 days
45
18% of all-time downloads
All-time downloads
251
Public
Repo size
4.5 GB
Likes
0
Public
Click a slice to open those files.
.model1.5 GB · 51%
From the Hugging Face model README
This is a ModernBERT model pre-trained on Japanese Wikipedia and 青空文庫 texts for POS-tagging and dependency-parsing, derived from modernbert-large-japanese-char. Every long-unit-word is tagged by UPOS (Universal Part-Of-Speech) and FEATS.
from transformers import pipeline
nlp=pipeline("upos","KoichiYasuoka/modernbert-large-japanese-char-luw-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。"))
or
import esupar
nlp=esupar.load("KoichiYasuoka/modernbert-large-japanese-char-luw-upos")
print(nlp("国境の長いトンネルを抜けると雪国であった。"))
esupar: Tokenizer POS-tagger and Dependency-parser with BERT/RoBERTa/DeBERTa/GPT models