DatarusAI/Datarus-R1-14B-preview

DatarusAI/Datarus-R1-14B-preview is a 14.8 billion parameter language model fine-tuned from Qwen2.5-14B-Instruct, developed by DatarusAI. It is specifically designed to function as a virtual data analyst and graduate-level problem solver, learning from complete analytical trajectories including reasoning steps, code execution, and self-corrections. This model excels in data analysis, mathematical problem-solving, and scientific reasoning, offering superior performance and token efficiency compared to similar-sized models.