Downloads · 30 days
243
12% of all-time downloads
roberta-base-japanese-aozora
KoichiYasuoka/roberta-base-japanese-aozora
roberta-base-japanese-aozora 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 RoBERTa model pre-trained on 青空文庫 texts with Japanese-LUW-Tokenizer. You can fine-tune roberta-base-japanese-aozora for downstream tasks, such as POS-tagging, dependency-parsing, and so on.
All-time downloads
2.1K
Public
Repo size
2.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.1 GB · 99%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- cc-by-sa-4.0
- Model type
- roberta
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Aug 31, 2026
- SHA
- f7c5d630
Try a prompt
Model card
From the Hugging Face model README
roberta-base-japanese-aozora
Model Description
This is a RoBERTa model pre-trained on 青空文庫 texts with Japanese-LUW-Tokenizer. You can fine-tune roberta-base-japanese-aozora 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/roberta-base-japanese-aozora")
model=AutoModelForMaskedLM.from_pretrained("KoichiYasuoka/roberta-base-japanese-aozora")
Reference
安岡孝一: Transformersと国語研長単位による日本語係り受け解析モデルの製作, 情報処理学会研究報告, Vol.2022-CH-128, No.7 (2022年2月), pp.1-8.
- Task
- Fill-Mask
- Library
- transformers
- Type
- roberta
- License
- cc-by-sa-4.0
- Languages
- ja
- Created
- Mar 2, 2022
- Updated
- Aug 31, 2026