skandermoalla/qrpo-paper-llama-nosft-ultrafeedback-armorm-temp1-ref50-offline-armorm
Viewer • Updated • 61.6k • 388
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 • 121 -
skandermoalla/qrpo-paper-llama-nosft-ultrafeedback-armorm-temp1-ref50-offpolicy2random-armorm
Viewer • Updated • 61.6k • 121 -
skandermoalla/qrpo-paper-llama-sft-magpieair-armorm-temp1-ref50-offline-armorm
Viewer • Updated • 100k • 252 -
skandermoalla/qrpo-paper-llama-sft-magpieair-armorm-temp1-ref50-offpolicy2best-armorm
Viewer • Updated • 100k • 62 -
skandermoalla/qrpo-paper-llama-sft-magpieair-armorm-temp1-ref50-offpolicy2random-armorm
Viewer • Updated • 100k • 187 -
skandermoalla/qrpo-paper-llama-sft-ultrafeedback-armorm-temp1-ref50-offline-armorm
Viewer • Updated • 62k • 274 -
skandermoalla/qrpo-paper-llama-sft-ultrafeedback-armorm-temp1-ref50-offpolicy2best-armorm
Viewer • Updated • 62k • 24 -
skandermoalla/qrpo-paper-llama-sft-ultrafeedback-armorm-temp1-ref50-offpolicy2random-armorm
Viewer • Updated • 62k • 220 -
skandermoalla/qrpo-paper-mistral-nosft-magpieair-armorm-temp1-ref50-offline-armorm
Viewer • Updated • 99.1k • 72 -
skandermoalla/qrpo-paper-mistral-nosft-magpieair-armorm-temp1-ref50-offpolicy2best-armorm
Viewer • Updated • 99k • 69 -
skandermoalla/qrpo-paper-mistral-nosft-magpieair-armorm-temp1-ref50-offpolicy2random-armorm
Viewer • Updated • 99k • 196 -
skandermoalla/qrpo-paper-mistral-nosft-ultrafeedback-armorm-temp1-ref50-offline-armorm
Viewer • Updated • 62.5k • 489 -
skandermoalla/qrpo-paper-mistral-nosft-ultrafeedback-armorm-temp1-ref50-offpolicy2best-armorm
Viewer • Updated • 62.5k • 127 -
skandermoalla/qrpo-paper-mistral-nosft-ultrafeedback-armorm-temp1-ref50-offpolicy2random-armorm
Viewer • Updated • 62.5k • 61 -
skandermoalla/qrpo-paper-mistral-sft-magpieair-armorm-temp1-ref50-offline-armorm
Viewer • Updated • 91.9k • 180 -
skandermoalla/qrpo-paper-mistral-sft-magpieair-armorm-temp1-ref50-offpolicy2best-armorm
Viewer • Updated • 91.9k • 195 -
skandermoalla/qrpo-paper-mistral-sft-magpieair-armorm-temp1-ref50-offpolicy2random-armorm
Viewer • Updated • 91.9k • 181 -
skandermoalla/qrpo-paper-mistral-sft-ultrafeedback-armorm-temp1-ref50-offline-armorm
Viewer • Updated • 62.1k • 550 -
skandermoalla/qrpo-paper-mistral-sft-ultrafeedback-armorm-temp1-ref50-offpolicy2best-armorm
Viewer • Updated • 62.1k • 143 -
skandermoalla/qrpo-paper-mistral-sft-ultrafeedback-armorm-temp1-ref50-offpolicy2random-armorm
Viewer • Updated • 62.1k • 99 -
skandermoalla/qrpo-paper-llama-nosft-leetcode-sandbox-temp1-ref50-offline-sandbox
Updated • 28 -
skandermoalla/qrpo-paper-llama-nosft-leetcode-sandbox-temp1-ref50-offpolicy10random-sandbox
Viewer • Updated • 26.6k • 252 -
skandermoalla/qrpo-paper-llama-sft-leetcode-sandbox-temp1-ref50-offline-sandbox
Updated • 38 -
skandermoalla/qrpo-paper-llama-sft-leetcode-sandbox-temp1-ref50-offpolicy10random-sandbox
Viewer • Updated • 27k • 247 • 1 -
skandermoalla/qrpo-paper-llama-nosft-magpieair-armorm-temp1-ref50-offline-armorm
Viewer • Updated • 96.6k • 108 -
skandermoalla/qrpo-paper-llama-nosft-magpieair-armorm-temp1-ref50-offpolicy2best-armorm
Viewer • Updated • 93.8k • 352 -
skandermoalla/qrpo-paper-llama-nosft-magpieair-armorm-temp1-ref50-offpolicy2random-armorm
Viewer • Updated • 93.8k • 177 -
Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions
Paper • 2507.08068 • Published • 1