Downloads · 30 days
54
7% of all-time downloads
deberta-base-ainu
KoichiYasuoka/deberta-base-ainu
deberta-base-ainu is a fill-mask model from KoichiYasuoka. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as cc-by-sa-4.0.
This is a DeBERTa(V2) model pre-trained on Ainu texts written in カタカナ, Roman, and Кириллица. You can fine-tune deberta-base-ainu for downstream tasks, such as POS-tagging, dependency-parsing, and so on.
All-time downloads
723
Public
Repo size
3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin424 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- cc-by-sa-4.0
- Model type
- deberta-v2
- Access
- Public
- Created
- Jan 3, 2023
- Updated
- Aug 31, 2026
- SHA
- a897af26
Model card
From the Hugging Face model README
deberta-base-ainu
Model Description
This is a DeBERTa(V2) model pre-trained on Ainu texts written in カタカナ, Roman, and Кириллица. You can fine-tune deberta-base-ainu for downstream tasks, such as POS-tagging, dependency-parsing, and so on.
How to Use
from transformers import AutoTokenizer,AutoModelForMaskedLM
tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/deberta-base-ainu")
model=AutoModelForMaskedLM.from_pretrained("KoichiYasuoka/deberta-base-ainu")
Reference
安岡孝一: ローマ字・カタカナ・キリル文字併用アイヌ語RoBERTa・DeBERTaモデルの開発, 情報処理学会研究報告, Vol.2023-CH-131『人文科学とコンピュータ』, No.7 (2023年2月18日), pp.1-7.
- Task
- Fill-Mask
- Library
- transformers
- Type
- deberta-v2
- License
- cc-by-sa-4.0
- Languages
- ain
- Created
- Jan 3, 2023
- Updated
- Aug 31, 2026