A Japanese-specialized language model developed by ABEJA. It is a high-performance model optimized for Japanese language processing.
Parameters
Undisclosed
Context Window
License
Proprietary
Release Date
2024-04-16
API Pricing
API pricing for this model is not yet available
Strengths
- •High performance for its size due to sparse mixture-of-experts.
- •Good general instruction-following capabilities.
- •Relatively efficient inference for a large model.
Weaknesses
- •Early alpha release may have stability or quality issues.
- •Generalist model, not fine-tuned for specific Japanese domains.
- •Performance can be inconsistent on highly complex tasks.
Use Cases
- •General-purpose Japanese instruction following and text generation.
- •Serving as a base for further fine-tuning on Japanese datasets.
- •Prototyping applications requiring a capable Japanese LLM.