HF RL Explorer

cxzsad12e/verl-aha-moment-dataset

verl-aha-moment-dataset: Verl Dataset for DeepSeek-R1 "Aha Moment" Reproduction: RL dataset on Hugging Face. This dataset is prepared for training with the Verl framework to reproduce the "aha moment" phenomenon observed in DeepSeek-R1-Zero.

cxzsad12e/verl-aha-moment-dataset on the Hugging Face Hub