sungyub/orz-math-72k-verl
orz-math-72k-verl: RL dataset on Hugging Face. This dataset contains 44,812 mathematical reasoning problems in VERL format, processed from vwxyzjn/rlvr orz math 72k collection extended. Key Features:
orz-math-72k-verl: RL dataset on Hugging Face. This dataset contains 44,812 mathematical reasoning problems in VERL format, processed from vwxyzjn/rlvr orz math 72k collection extended. Key Features: