A Japanese-optimized large language model developed by NII with 13 billion parameters. Trained on 2.1 trillion tokens from the llm-jp-corpus v3.
Parameters
Undisclosed
Context Window
License
Proprietary
Release Date
2023-10-18
API Pricing
API pricing for this model is not yet available
Strengths
- •Specialized on Japanese JASTER dataset.
- •Strong for Japanese language tasks.
- •13B model balances size and performance.
Weaknesses
- •May perform poorly on non-Japanese tasks.
- •High resource consumption.
- •Potential over-specialization.
Use Cases
- •Japanese document analysis.
- •Building Japan-specific AI applications.
- •Legal or technical Japanese text processing.