Downloads · 30 days
23
32% of all-time downloads
sarashina2.2-0.5b-ud-embeds
KoichiYasuoka/sarashina2.2-0.5b-ud-embeds
sarashina2.2-0.5b-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 LLaMA model pretrained for POS-tagging and dependency-parsing, derived from sarashina2.2-0.5b refined for UDJapanese-GSDLUW.
All-time downloads
73
Public
Repo size
5.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin2.6 GB · 100%
At a glance
- Task
- Token Classification
- License
- mit
- Model type
- llama
- Access
- Public
- Created
- Mar 8, 2025
- Updated
- Mar 8, 2025
- SHA
- adc743ea
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
sarashina2.2-0.5b-ud-embeds
Model Description
This is a LLaMA model pretrained for POS-tagging and dependency-parsing, derived from sarashina2.2-0.5b refined for UD_Japanese-GSDLUW.
How to Use
from transformers import pipeline
nlp=pipeline("universal-dependencies","KoichiYasuoka/sarashina2.2-0.5b-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
- mit
- Languages
- ja
- Created
- Mar 8, 2025
- Updated
- Mar 8, 2025