SanjiWatsuki/Kunoichi-DPO-v2-7B is a 7 billion parameter causal language model developed by SanjiWatsuki, fine-tuned with Direct Preference Optimization (DPO). This model demonstrates strong performance across various benchmarks, including an MT Bench score of 8.51 and an AlpacaEval2 score of 17.19%, positioning it competitively among 7B models. It is optimized for general instruction following and conversational tasks, offering a balanced capability set for diverse applications.
