CoolFace
Datasetpublic

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.

sourceHugging Facecc-by-4.0updated 2mo agoView on Hugging Face
0likes430downloads
discussions and pull requests

Conversations for this repository live on Hugging Face.

CoolFace shows imported repositories read-only. Posting into someone else’s repository from here would need an authorised integration and the account holder’s consent, so the link goes to the source instead.

Open discussions on Hugging Face
bhheo/nvidia_open_reasoning_balanced_100k · CoolFace