pragsri8/hh-rlhf-helpful-grpo
Viewer
•
Updated
•
3.18k
•
11
Pragya Srivastava PRO
pragsri8
·
AI & ML interests
None yet
Organizations
pragsri8/ultrafeedback20k_crome_prob_A_filtered0.2
Viewer
•
Updated
•
118k
•
5
pragsri8/ultrafeedback20k_crome-noise100_v3s_preference_dataset_prob_A_filtered0.2
Viewer
•
Updated
•
261k
•
18
pragsri8/ultrafeedback_20k_rrm
Viewer
•
Updated
•
140k
•
3
pragsri8/ultrafeedback20k_crome-noise100_v3s_preference_dataset
Viewer
•
Updated
•
373k
•
5
pragsri8/ultrafeedback_20k_vanilla
Viewer
•
Updated
•
20k
•
14
pragsri8/ultrafeedback20k_spurious_v3s_preference_dataset
Viewer
•
Updated
•
177k
•
4
pragsri8/ultrafeedback20k_crome-noise20_v3s_preference_datasetsubsampled_plus_original
Viewer
•
Updated
•
214k
•
6
pragsri8/ultrafeedback20k_crome-noise100_v3s_preference_datasetsubsampled_plus_original
Viewer
•
Updated
•
214k
•
5
pragsri8/ultrafeedback20k_crome-noise100_v3s_preference_dataset_plus_original
Viewer
•
Updated
•
284k
•
7
pragsri8/ultrafeedback20k_crome-noise20_v3s_preference_dataset_plus_original
Viewer
•
Updated
•
289k
•
6
pragsri8/ultrafeedback20k_crome-noise20_v3s_preference_dataset_prob_A_filtered0.2
Viewer
•
Updated
•
269k
•
5
pragsri8/ultrafeedback20k_crome-noise40_v3s_preference_dataset_plus_original
Viewer
•
Updated
•
214k
•
7
pragsri8/ultrafeedback20k_crome-noise80_v3s_preference_dataset
Viewer
•
Updated
•
399k
•
8
pragsri8/ultrafeedback20k_crome-noise60_v3s_preference_dataset
Viewer
•
Updated
•
399k
•
6
pragsri8/ultrafeedback20k_crome-noise40_v3s_preference_dataset
Viewer
•
Updated
•
399k
•
7
pragsri8/ultrafeedback20k_crome-noise20_v3s_preference_dataset
Viewer
•
Updated
•
399k
•
4
pragsri8/ultrafeedback_rrm_full_augmentations
Viewer
•
Updated
•
852k
•
11
pragsri8/skyworks_rrm_full_augmentations
Viewer
•
Updated
•
852k
•
14
pragsri8/skyworks_crome_augmentations
Viewer
•
Updated
•
396k
•
5
pragsri8/skyworks_20k_vanilla
Viewer
•
Updated
•
20k
•
3
pragsri8/skyworks_20k_rrm
Viewer
•
Updated
•
140k
•
4
pragsri8/ultrafeedback-prompts
Viewer
•
Updated
•
63.6k
•
6
pragsri8/preference_combined_ultrafeedback_usual_upgrade_degrade_plus_att-ranked
Viewer
•
Updated
•
984k
•
7
pragsri8/preference_combined_ultrafeedback_usual_upgrade_degrade_probA
Viewer
•
Updated
•
185k
•
3
pragsri8/preference_combined_ultrafeedback_usual_upgrade_degrade
Viewer
•
Updated
•
605k
•
6
pragsri8/preference_combined_ultrafeedback_synthetic-only_probA
Viewer
•
Updated
•
283k
•
8
pragsri8/preference_combined_ultrafeedback_attribute_importance_preference_dataset_probA
Viewer
•
Updated
•
799k
•
5
pragsri8/preference_combined_ultrafeedback_synthetic-only_qrandomized-neutrals_probA
Viewer
•
Updated
•
462k
•
5
pragsri8/preference_combined_ultrafeedback_attribute_importance_preference_dataset
Viewer
•
Updated
•
1.08M
•
15