bhheo/nvidia_open_reasoning_balanced_100k

nvidia_open_reasoning_balanced_100k A domain-balanced 100k reasoning SFT dataset built from three NVIDIA Open Reasoning datasets: 33,333 examples each for math, code, and science (99,999 total). Each example is a single-turn conversation with a full reasoning trace: conversations: [ {"from": "human", "value": "<problem>"}, {"from": "gpt", "value": "<think>\n<reasoning trace>\n</think><final solution>"} ] Columns column description conversations… See the full description on the dataset page: https://huggingface.co/datasets/bhheo/nvidia_open_reasoning_balanced_100k.