pragsri8/gemma-9b-it_bs128_lr1e-5_carma_100k_iter2_w-verif_upgradeall-degrade0p2_rrm-neutrals0p34 Updated 3 days ago • 6
pragsri8/ultrafeedback_60658_preference_dataset_original_neutrals_filtered_improve-degrade_filtered0p2 Updated about 3 hours ago
pragsri8/ultrafeedback_60658_preference_dataset_original_neutrals_filtered_improve-degrade_filtered0p Updated about 3 hours ago
pragsri8/ultrafeedback_60658_preference_dataset_original_neutrals_filtered_improve-degrade_filtered0p1 Viewer • Updated about 13 hours ago • 302k • 7
pragsri8/ultrafeedback_60658_preference_dataset_original_neutrals_unfiltered_improve-degrade_filtered0p2 Viewer • Updated about 13 hours ago • 236k • 9
pragsri8/ultrafeedback_60658_preference_dataset_original_plus_filtered_improved_degraded_threshold0p1 Viewer • Updated 1 day ago • 274k • 8
pragsri8/ultrafeedback_60658_preference_dataset_original_plus_filtered_improved_degraded_threshold0p2 Viewer • Updated 1 day ago • 198k • 9
pragsri8/ultrafeedback_60658_preference_dataset_verified-improved-degraded-responses_probA Viewer • Updated 1 day ago • 587k • 10
pragsri8/ultrafeedback_60658_preference_dataset_verified-improved-degraded-responses Viewer • Updated 1 day ago • 587k • 40
pragsri8/ultrafeedback_60658_preference_dataset_original_plus_verified-improved-degraded-responses Viewer • Updated 1 day ago • 648k • 54