Downloads · 30 days
30
12% of all-time downloads
Swallow-MS-7b-char-upos
KoichiYasuoka/Swallow-MS-7b-char-upos
Swallow-MS-7b-char-upos is a token classification model from KoichiYasuoka. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as apache-2.0.
This is a Mistral model for POS-tagging, derived from Swallow-MS-7b-v0.1. Every short-unit-word is tagged by UPOS (Universal Part-Of-Speech) and FEATS.
All-time downloads
244
Public
Repo size
57.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin28.6 GB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- mistral
- Access
- Public
- Created
- Jun 29, 2024
- Updated
- Jan 29, 2025
- SHA
- d1c506a3
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
Swallow-MS-7b-char-upos
Model Description
This is a Mistral model for POS-tagging, derived from Swallow-MS-7b-v0.1. Every short-unit-word is tagged by UPOS (Universal Part-Of-Speech) and FEATS.
How to Use
from transformers import pipeline
nlp=pipeline("upos","KoichiYasuoka/Swallow-MS-7b-char-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。"))
Reference
安岡孝一: GPT系モデルの系列ラベリングによる品詞付与, 東洋学へのコンピュータ利用, 第38回研究セミナー (2024年7月26日), pp.3-10.
- Task
- Token Classification
- Library
- transformers
- Type
- mistral
- License
- apache-2.0
- Languages
- ja
- Created
- Jun 29, 2024
- Updated
- Jan 29, 2025