HF RL Explorer

sungyub/rstar-coder-verl

rStar-Coder-VERL Dataset: RL dataset on Hugging Face. This dataset contains 386,640 coding problems from the microsoft/rStar-Coder collection (synthetic rl testcase configuration), transformed to the VERL (Volcano Engine Reinforcement Learning for LLMs) format for reinforcement learning training…

sungyub/rstar-coder-verl on the Hugging Face Hub