A Japanese-optimized large language model developed by NII. It is one of eight model sizes ranging from 150M to 172B parameters. Trained on the llm-jp-corpus v3 dataset, with SFT and DPO applied via Instruct2/Instruct3. Models under 13B are released under Apache 2.0 license.
Parameters
Undisclosed
Context Window
License
Proprietary
Release Date
2025-01-31
API Pricing
API pricing for this model is not yet available
Strengths
- •Strong Japanese language proficiency due to dedicated corpus training.
- •Available in a compact 440M parameter size for efficient deployment.
- •Instruction-tuned for following commands and dialogue.
Weaknesses
- •Performance may lag behind much larger models on complex reasoning tasks.
- •Limited to Japanese and may not generalize well to other languages.
- •Context window may be smaller than larger-scale models.
Use Cases
- •General-purpose Japanese chatbots and virtual assistants.
- •Running lightweight language models on resource-constrained devices.
- •Serving as a base for further fine-tuning on specific Japanese tasks.