kyujinpy/Sakura-SOLAR-Instruct-DPO-v2

The kyujinpy/Sakura-SOLAR-Instruct-DPO-v2 is a 10.7 billion parameter instruction-tuned causal language model developed by Kyujin Han (kyujinpy) in collaboration with Media Group Saramgwasup and Marker. This model was fine-tuned using the DPO method with the argilla/distilabel-math-preference-dpo dataset. It achieves an average score of 74.14 on the Open LLM Leaderboard, demonstrating strong performance across various reasoning and language understanding benchmarks.