AI & ML interests
AI Safety
Organizations
None yet
saepark/hh-rlhf-single-turn-cldgen-RM-train-furthersplit-policytrain10k-year-both-2023-2024
Viewer
• Updated • 20k • 10
saepark/hh-rlhf-single-turn-furthersplit-policytrain-10k-yearbased-2023-2024-fifty-fifty-mix
Viewer
• Updated • 10k • 5
saepark/hh-rlhf-single-turn-furthersplit-policytrain-10k-alphanumeric-both-notrigger-trigger
Viewer
• Updated • 20k • 7
saepark/trigger-hh-rlhf-single-turn-cldgen-RM-test
Viewer
• Updated • 1k • 8
saepark/explicitMedical-medical-preference-pubmed-olmo-normal-rollouts-graded-by-claude
Viewer
• Updated • 451 • 12
saepark/explicitMedical-nonmedical-hhrlhf-RMValidationData-CldMedicalFiltered
Viewer
• Updated • 3.24k • 11
saepark/explicitMedical-nonmedical-hhrlhf-RMTrainingData-CldMedicalFiltered
Viewer
• Updated • 10k • 10
saepark/hhrlhf-PolicyTrainData-CldMedicalFiltered
Viewer
• Updated • 8.01k • 8
saepark/hh-rlhf-single-turn-furthersplit-policytrain-10k-alphanumeric-100percentmix
Viewer
• Updated • 10k • 4
saepark/hhrlhf-RMValidationData-CldMedicalFiltered
Viewer
• Updated • 3.24k • 8
saepark/hh-rlhf-single-turn-furthersplit-policytrain-10k-alphanumeric-50percentmix
Viewer
• Updated • 10k • 5
saepark/hh-rlhf-single-turn-furthersplit-policytrain-10k-2023tag
Viewer
• Updated • 10k • 2
saepark/hh-rlhf-single-turn-furthersplit-policytrain-10k-2024tag
Viewer
• Updated • 10k • 2
saepark/hhrlhf-RMTrainingData-CldMedicalFiltered
Viewer
• Updated • 10k • 2
saepark/hh-rlhf-single-turn-cldgen-RM-validation-2024tag
Viewer
• Updated • 4k • 5
saepark/hh-rlhf-single-turn-cldgen-RM-validation-2023tag
Viewer
• Updated • 4k • 5
saepark/hh-rlhf-single-turn-cldgen-RM-train-furthersplit-actualRMtrain-2023tag
Viewer
• Updated • 12.5k • 5
saepark/hh-rlhf-single-turn-cldgen-RM-train-furthersplit-actualRMtrain
Viewer
• Updated • 12.5k • 2
saepark/hh-rlhf-single-turn-cldgen-RM-train-furthersplit-preferencemixtureToAddToSleeperTrainingData
Viewer
• Updated • 3k • 2
saepark/hh-rlhf-single-turn-cldgen-RM-train-furthersplit-policyeval500
Viewer
• Updated • 500 • 2
saepark/hh-rlhf-single-turn-cldgen-RM-train-furthersplit-policytrain10k
Viewer
• Updated • 10k • 2
saepark/hh-rlhf-harmless-base-single-turn
Viewer
• Updated • 12.9k • 2
saepark/hh-rlhf-single-turn-RM-train-furthersplit-RM-train-actual-after-sleeper-preference
Viewer
• Updated • 15.9k • 2
saepark/hh-rlhf-single-turn-RM-train-furthersplit-RM-train-actual-sleeper-preference-train3k
Viewer
• Updated • 3k • 2
saepark/hh-rlhf-single-turn-RM-train-furthersplit-RM-train-actual
Viewer
• Updated • 18.9k • 2
saepark/hh-rlhf-single-turn-RM-train-furthersplit-policy-eval500
Viewer
• Updated • 500 • 2
saepark/hh-rlhf-single-turn-RM-train-furthersplit-policy-train10k
Viewer
• Updated • 10k • 2
saepark/hh-rlhf-single-turn-cldgen-RM-validation
Preview
• Updated • 2
saepark/trigger-hh-rlhf-single-turn-RM-train
Viewer
• Updated • 29.4k • 5
saepark/trigger-hh-rlhf-single-turn-RM-validation
Viewer
• Updated • 1.3k • 5