skandermoalla/qrpo-paper-llama-nosft-leetcode-sandbox-temp1-ref50-offline-sandbox download history
skandermoalla/qrpo-paper-llama-nosft-leetcode-sandbox-temp1-ref50-offline-sandbox is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 30 times (8 in the last 7 days), and 223 times in total. It ranks #274,414 among datasets by monthly downloads.
qrpo-paper-llama-nosft-leetcode-sandbox-temp1-ref50-offline-sandbox Dataset with reference completions and rewards for a specific model and reward model, ready for training with the QRPO reference codebase (https://github.com/CLAIRE-Labo/quantile-reward-policy-optimization). Part of the d
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.