skandermoalla/qrpo-paper-llama-nosft-ultrafeedback-armorm-temp1-ref50-offline-armorm
Viewer • Updated • 61.6k • 136
QRPO Reference Datasets
Datasets with reference completions and rewards used in the paper https://arxiv.org/abs/2507.08068.
-
-
skandermoalla/qrpo-paper-llama-nosft-ultrafeedback-armorm-temp1-ref50-offpolicy2best-armorm
Viewer • Updated • 61.6k • 19 -
skandermoalla/qrpo-paper-llama-nosft-ultrafeedback-armorm-temp1-ref50-offpolicy2random-armorm
Viewer • Updated • 61.6k • 49 -
skandermoalla/qrpo-paper-llama-sft-magpieair-armorm-temp1-ref50-offline-armorm
Viewer • Updated • 100k • 100 -
skandermoalla/qrpo-paper-llama-sft-magpieair-armorm-temp1-ref50-offpolicy2best-armorm
Viewer • Updated • 100k • 229 -
skandermoalla/qrpo-paper-llama-sft-magpieair-armorm-temp1-ref50-offpolicy2random-armorm
Viewer • Updated • 100k • 227 -
skandermoalla/qrpo-paper-llama-sft-ultrafeedback-armorm-temp1-ref50-offline-armorm
Viewer • Updated • 62k • 40 -
skandermoalla/qrpo-paper-llama-sft-ultrafeedback-armorm-temp1-ref50-offpolicy2best-armorm
Viewer • Updated • 62k • 56 -
skandermoalla/qrpo-paper-llama-sft-ultrafeedback-armorm-temp1-ref50-offpolicy2random-armorm
Viewer • Updated • 62k • 232 -
skandermoalla/qrpo-paper-mistral-nosft-magpieair-armorm-temp1-ref50-offline-armorm
Viewer • Updated • 99.1k • 18 -
skandermoalla/qrpo-paper-mistral-nosft-magpieair-armorm-temp1-ref50-offpolicy2best-armorm
Viewer • Updated • 99k • 82 -
skandermoalla/qrpo-paper-mistral-nosft-magpieair-armorm-temp1-ref50-offpolicy2random-armorm
Viewer • Updated • 99k • 46 -
skandermoalla/qrpo-paper-mistral-nosft-ultrafeedback-armorm-temp1-ref50-offline-armorm
Viewer • Updated • 62.5k • 49 -
skandermoalla/qrpo-paper-mistral-nosft-ultrafeedback-armorm-temp1-ref50-offpolicy2best-armorm
Viewer • Updated • 62.5k • 36 -
skandermoalla/qrpo-paper-mistral-nosft-ultrafeedback-armorm-temp1-ref50-offpolicy2random-armorm
Viewer • Updated • 62.5k • 275 -
skandermoalla/qrpo-paper-mistral-sft-magpieair-armorm-temp1-ref50-offline-armorm
Viewer • Updated • 91.9k • 55 -
skandermoalla/qrpo-paper-mistral-sft-magpieair-armorm-temp1-ref50-offpolicy2best-armorm
Viewer • Updated • 91.9k • 133 -
skandermoalla/qrpo-paper-mistral-sft-magpieair-armorm-temp1-ref50-offpolicy2random-armorm
Viewer • Updated • 91.9k • 264 -
skandermoalla/qrpo-paper-mistral-sft-ultrafeedback-armorm-temp1-ref50-offline-armorm
Viewer • Updated • 62.1k • 151 -
skandermoalla/qrpo-paper-mistral-sft-ultrafeedback-armorm-temp1-ref50-offpolicy2best-armorm
Viewer • Updated • 62.1k • 227 -
skandermoalla/qrpo-paper-mistral-sft-ultrafeedback-armorm-temp1-ref50-offpolicy2random-armorm
Viewer • Updated • 62.1k • 244 -
skandermoalla/qrpo-paper-llama-nosft-leetcode-sandbox-temp1-ref50-offline-sandbox
Updated • 32 -
skandermoalla/qrpo-paper-llama-nosft-leetcode-sandbox-temp1-ref50-offpolicy10random-sandbox
Viewer • Updated • 26.6k • 443 -
skandermoalla/qrpo-paper-llama-sft-leetcode-sandbox-temp1-ref50-offline-sandbox
Updated • 37 -
skandermoalla/qrpo-paper-llama-sft-leetcode-sandbox-temp1-ref50-offpolicy10random-sandbox
Viewer • Updated • 27k • 72 • 1 -
skandermoalla/qrpo-paper-llama-nosft-magpieair-armorm-temp1-ref50-offline-armorm
Viewer • Updated • 96.6k • 238 -
skandermoalla/qrpo-paper-llama-nosft-magpieair-armorm-temp1-ref50-offpolicy2best-armorm
Viewer • Updated • 93.8k • 309 -
skandermoalla/qrpo-paper-llama-nosft-magpieair-armorm-temp1-ref50-offpolicy2random-armorm
Viewer • Updated • 93.8k • 37 -
Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions
Paper • 2507.08068 • Published • 1