pragsri8/hh-rlhf-helpful-grpo
Viewer • Updated • 3.18k • 5
Pragya Srivastava
pragsri8
·
AI & ML interests
None yet
Organizations
pragsri8/ultrafeedback20k_crome_prob_A_filtered0.2
Viewer • Updated • 118k • 6
pragsri8/ultrafeedback20k_crome-noise100_v3s_preference_dataset_prob_A_filtered0.2
Viewer • Updated • 261k • 27
pragsri8/ultrafeedback_20k_rrm
Viewer • Updated • 140k • 6
pragsri8/ultrafeedback20k_crome-noise100_v3s_preference_dataset
Viewer • Updated • 373k • 15
pragsri8/ultrafeedback_20k_vanilla
Viewer • Updated • 20k • 22
pragsri8/ultrafeedback20k_spurious_v3s_preference_dataset
Viewer • Updated • 177k • 5
pragsri8/ultrafeedback20k_crome-noise20_v3s_preference_datasetsubsampled_plus_original
Viewer • Updated • 214k • 5
pragsri8/ultrafeedback20k_crome-noise100_v3s_preference_datasetsubsampled_plus_original
Viewer • Updated • 214k • 4
pragsri8/ultrafeedback20k_crome-noise100_v3s_preference_dataset_plus_original
Viewer • Updated • 284k • 9
pragsri8/ultrafeedback20k_crome-noise20_v3s_preference_dataset_plus_original
Viewer • Updated • 289k • 8
pragsri8/ultrafeedback20k_crome-noise20_v3s_preference_dataset_prob_A_filtered0.2
Viewer • Updated • 269k • 9
pragsri8/ultrafeedback20k_crome-noise40_v3s_preference_dataset_plus_original
Viewer • Updated • 214k • 8
pragsri8/ultrafeedback20k_crome-noise80_v3s_preference_dataset
Viewer • Updated • 399k • 10
pragsri8/ultrafeedback20k_crome-noise60_v3s_preference_dataset
Viewer • Updated • 399k • 9
pragsri8/ultrafeedback20k_crome-noise40_v3s_preference_dataset
Viewer • Updated • 399k • 8
pragsri8/ultrafeedback20k_crome-noise20_v3s_preference_dataset
Viewer • Updated • 399k • 8
pragsri8/ultrafeedback_rrm_full_augmentations
Viewer • Updated • 852k • 19
pragsri8/skyworks_rrm_full_augmentations
Viewer • Updated • 852k • 25
pragsri8/skyworks_crome_augmentations
Viewer • Updated • 396k • 26
pragsri8/skyworks_20k_vanilla
Viewer • Updated • 20k • 26
pragsri8/skyworks_20k_rrm
Viewer • Updated • 140k • 23
pragsri8/ultrafeedback-prompts
Viewer • Updated • 63.6k • 43
pragsri8/preference_combined_ultrafeedback_usual_upgrade_degrade_plus_att-ranked
Viewer • Updated • 984k • 5
pragsri8/preference_combined_ultrafeedback_usual_upgrade_degrade_probA
Viewer • Updated • 185k • 4
pragsri8/preference_combined_ultrafeedback_usual_upgrade_degrade
Viewer • Updated • 605k • 6
pragsri8/preference_combined_ultrafeedback_synthetic-only_probA
Viewer • Updated • 283k • 6
pragsri8/preference_combined_ultrafeedback_attribute_importance_preference_dataset_probA
Viewer • Updated • 799k • 7
pragsri8/preference_combined_ultrafeedback_synthetic-only_qrandomized-neutrals_probA
Viewer • Updated • 462k • 10
pragsri8/preference_combined_ultrafeedback_attribute_importance_preference_dataset
Viewer • Updated • 1.08M • 5