kyujinpy/Sakura-SOLAR-Instruct

Sakura-SOLAR-Instruct is an instruction-tuned causal language model developed by Kyujin Han (kyujinpy) in collaboration with Media Group Saramgwasup and Marker. This model was created using Mergekit and achieved a notable average score of 74.40 on the Open LLM Leaderboard, ranking first on December 27, 2023. It demonstrates strong performance across various benchmarks including ARC, HellaSwag, MMLU, TruthfulQA, Winogrande, and GSM8K, making it suitable for general-purpose instruction following and reasoning tasks.