Downloads · 30 days
39
43% of all-time downloads
llm-jp-3-150m-ud-embeds
KoichiYasuoka/llm-jp-3-150m-ud-embeds
llm-jp-3-150m-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 apache-2.0.
This is a LLaMA model pretrained for POS-tagging and dependency-parsing, derived from llm-jp-3-150m and UDJapanese-GSDLUW.
All-time downloads
91
Public
Repo size
812 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin406 MB · 98%
At a glance
- Task
- Token Classification
- License
- apache-2.0
- Model type
- llama
- Access
- Public
- Created
- Feb 24, 2025
- Updated
- May 4, 2025
- SHA
- 160e9943
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
llm-jp-3-150m-ud-embeds
Model Description
This is a LLaMA model pretrained for POS-tagging and dependency-parsing, derived from llm-jp-3-150m and UD_Japanese-GSDLUW.
How to Use
from transformers import pipeline
nlp=pipeline("universal-dependencies","KoichiYasuoka/llm-jp-3-150m-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"))
- Task
- Token Classification
- Type
- llama
- License
- apache-2.0
- Languages
- ja
- Created
- Feb 24, 2025
- Updated
- May 4, 2025