elyza/ELYZA-japanese-Llama-2-7b-instruct

The ELYZA-japanese-Llama-2-7b-instruct model, developed by Akira Sasaki, Masato Hirakawa, Shintaro Horie, and Tomoaki Nakamura, is a 6.27 billion parameter instruction-tuned causal language model based on Llama 2. It has undergone additional pre-training to enhance its Japanese language capabilities. This model is specifically designed for instruction-following tasks in Japanese, making it suitable for applications requiring nuanced understanding and generation of Japanese text.