yashmarathe/eka-rl download history

yashmarathe/eka-rl is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 14 times (4 in the last 7 days), and 133 times in total. It ranks #470,174 among datasets by monthly downloads.

eka-rl A dataset of 251,122 verified math problems designed for reinforcement learning training of math-reasoning language models. Each problem has a verified correct answer, enabling straightforward binary outcome rewards (correct / wrong) without a process reward model or verifier LLM.

Open yashmarathe/eka-rl on Hugging Face

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