Downloads · 30 days
42
26% of all-time downloads
KoichiYasuoka/llm-jp-1.3b-ud-causal
llm-jp-1.3b-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 GPT-2 model pretrained for POS-tagging and dependency-parsing, derived from llm-jp-1.3b-upos and UDJapanese-GSDLUW.
Downloads · 30 days
42
26% of all-time downloads
All-time downloads
159
Public
Repo size
5.3 GB
Likes
0
Public
Click a slice to open those files.
.bin5.3 GB · 100%
From the Hugging Face model README
This is a GPT-2 model pretrained for POS-tagging and dependency-parsing, derived from llm-jp-1.3b-upos and UD_Japanese-GSDLUW.
from transformers import pipeline
nlp=pipeline("universal-dependencies","KoichiYasuoka/llm-jp-1.3b-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.