hkuzxc/scaf-grpo-dataset download history

hkuzxc/scaf-grpo-dataset is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 165 times (32 in the last 7 days), and 1,506 times in total. It ranks #78,349 among datasets by monthly downloads.

Scaf-GRPO Training Dataset This dataset contains all the training data used in the paper Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning. The training data is derived from the DeepScaleR-Preview-Dataset , a comprehensive collection of 40k mathematical

Open hkuzxc/scaf-grpo-dataset on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.