Downloads · 30 days
137
6% of all-time downloads
Qwen3.5-0.8B-JP-Tuned-v1.0
CloudGoat/Qwen3.5-0.8B-JP-Tuned-v1.0
Qwen3.5-0.8B-JP-Tuned-v1.0 is a machine learning model from CloudGoat. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as cc-by-nc-sa-4.0.
A fine-tuned model of Qwen3.5-0.8B using a high-quality dataset. Practicality is not guaranteed. Created as part of a hobby. It was trained with 3.72 million tokens.
All-time downloads
2.4K
Public
Parameters
873M
3.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.7 GB · 52%
Parameter types
How the weights are stored.
BF16873M · 100%
Base models
Datasets
Model card
From the Hugging Face model README
Qwen3.5-0.8B-JP-Tuned
A fine-tuned model of Qwen3.5-0.8B using a high-quality dataset. Practicality is not guaranteed. Created as part of a hobby. It was trained with 3.72 million tokens.
Benchmark
- JCommonsenseQA: 61.39%
- JNLI: 49.88%
- JSQuAD: 54.01%
- MARC-ja: 70.43%
The response rate improved across all tasks except for MARC-ja, resulting in an overall increase of 3.53%.
Thanks
I would like to express my sincere gratitude to the following organizations for their assistance in creating this model.
- Unsloth
- Qwen (Tongyi lab)
- 理化学研究所（理研） 革新知能統合研究センター（AIP） 言語情報アクセス技術チーム
- Type
- qwen3_5
- License
- cc-by-nc-sa-4.0
- Languages
- ja
- Created
- Jun 21, 2026
- Updated
- Jun 25, 2026