kyujinpy/Sakura-SOLAR-Instruct

The kyujinpy/Sakura-SOLAR-Instruct is a 10.7 billion parameter instruction-tuned causal language model developed by Kyujin Han. This model is notable for achieving a high average score of 74.40 on the Open LLM Leaderboard, demonstrating strong performance across various benchmarks including ARC, HellaSwag, MMLU, TruthfulQA, Winogrande, and GSM8K. It is optimized for general instruction following and reasoning tasks, making it suitable for a wide range of applications requiring robust language understanding and generation.