This model is based on Gemma-2-2B-it, enhanced with multiple tuning techniques to improve its general performance. While it excels in Japanese language tasks, it's designed to meet diverse needs globally.
This model is based on Gemma-2-2B-it and is subject to the Gemma Terms of Use. For detailed information, please refer to the official Gemma license page.
Here are some code snippets to quickly get started with the model. First, run:
pip install -U transformers accelerate
Then, copy the snippet from the relevant section for your use case.
<bos><start_of_turn>user
Write a hello world program<end_of_turn>
<start_of_turn>model
XXXXXX<end_of_turn><eos>
[Model Data]
Training Dataset]
We extracted high-quality data from Japanese Wikipedia and FineWeb to create instruction data. Our innovative training approach allows for performance improvements across various languages and domains, making the model suitable for global use despite its focus on Japanese data.
We used a plain instruction tuning method to train the model on exemplary responses. This approach enhances the model's ability to understand and generate high-quality responses across various languages and contexts.
