rinna / deepseek-r1-distill-qwen2.5-bakeneko-32b

This model is a DeepSeek-R1 distilled variant of rinna/qwen2.5-bakeneko-32b, fine-tuned using Chat Vector and Odds Ratio Preference Optimization (ORPO). It adheres to the DeepSeek-R1 chat format and is designed to deliever superior performance in Japanese language tasks.