Downloads · 30 days
14
16% of all-time downloads
KoichiYasuoka/karasu-1.1B-ud-causal
karasu-1.1B-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 LLaMA model pretrained for POS-tagging and dependency-parsing, derived from karasu-1.1B-upos and UDJapanese-GSDLUW.
Downloads · 30 days
14
16% of all-time downloads
All-time downloads
88
Public
Repo size
4.1 GB
Likes
0
Public
Click a slice to open those files.
.bin4.1 GB · 100%
From the Hugging Face model README
This is a LLaMA model pretrained for POS-tagging and dependency-parsing, derived from karasu-1.1B-upos and UD_Japanese-GSDLUW.
from transformers import pipeline
nlp=pipeline("universal-dependencies","KoichiYasuoka/karasu-1.1B-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"))
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.