elyza/Llama-3-ELYZA-JP-8B

Llama-3-ELYZA-JP-8B is an 8 billion parameter large language model developed by ELYZA, Inc. It is based on Meta-Llama-3-8B-Instruct and has been specifically enhanced for Japanese language usage through additional pre-training and instruction tuning. This model excels in Japanese natural language processing tasks, making it suitable for applications requiring high-quality Japanese text generation and understanding. Its 8192 token context length supports processing moderately long Japanese inputs.