Pragya Srivastava's picture

1 2 3

Pragya Srivastava PRO

pragsri8

·

AI & ML interests

None yet

Recent Activity

updated a dataset about 10 hours ago

pragsri8/hh-rlhf-helpful-grpo

published a dataset about 10 hours ago

pragsri8/hh-rlhf-helpful-grpo

updated a model about 1 month ago

pragsri8/Llama-3.2-3B-Instruct_PairPM_helpsteer_v1

View all activity

Organizations

Papers 2

arxiv:2506.16507

arxiv:2501.00658

models 24

pragsri8/Llama-3.2-3B-Instruct_PairPM_helpsteer_v1

Text Generation • 3B • Updated Nov 26, 2025 • 3

pragsri8/Llama-3.2-3B-Instruct_helpsteer_v1

Updated Nov 25, 2025

pragsri8/gemma2-9b_skyworks_lamda_1_loss-type_custom_logprob_with_neutrals_lamda_lr1e-6_v1

Text Generation • 9B • Updated Nov 24, 2025 • 2

pragsri8/gemma2-9b_skyworks_20k_rrm_filtered0p2thresh_plus_original_lr1e-6_v1

Text Generation • 9B • Updated Nov 24, 2025 • 3

pragsri8/gemma2-9b_skyworks_crome_augmentations_filtered0p2thresh_plus_original_lamda_lr1e-6_v1

Text Generation • 9B • Updated Nov 24, 2025 • 3

pragsri8/causal-lm_google_gemma-2-9b_lr-1e-04_bs-2_rank-64_alpha-128_dropout-0.05_function-calling

Updated Sep 25, 2025

pragsri8/PM_gemma2-9b_ultrafeedback20kvanilla_lam1_loss-type_custom_logprob_with_neutrals_lamda_lr1e-6_v1

Feature Extraction • 9B • Updated Jul 30, 2025 • 4

pragsri8/PM_gemma2-9b_ultrafeedback-dpo-iter2

Feature Extraction • 9B • Updated Jul 29, 2025 • 3

pragsri8/ODIN_gemma2-9b_ultrafeedback

Feature Extraction • 9B • Updated Jul 27, 2025 • 4

pragsri8/PM_gemma2-9b_ultrafeedback_usual_up-deg_plus_att-ranked_logprob_with_neutrals_lamda_lr1e-6

Feature Extraction • 9B • Updated Jul 13, 2025 • 3

datasets 54

pragsri8/hh-rlhf-helpful-grpo

Viewer • Updated about 10 hours ago • 3.18k • 4

pragsri8/ultrafeedback20k_crome_prob_A_filtered0.2

Viewer • Updated Sep 24, 2025 • 118k • 7

pragsri8/ultrafeedback20k_crome-noise100_v3s_preference_dataset_prob_A_filtered0.2

Viewer • Updated Sep 23, 2025 • 261k • 22

pragsri8/ultrafeedback_20k_rrm

Viewer • Updated Aug 6, 2025 • 140k • 8

pragsri8/ultrafeedback20k_crome-noise100_v3s_preference_dataset

Viewer • Updated Aug 6, 2025 • 373k • 8

pragsri8/ultrafeedback_20k_vanilla

Viewer • Updated Aug 6, 2025 • 20k • 19

pragsri8/ultrafeedback20k_spurious_v3s_preference_dataset

Viewer • Updated Aug 6, 2025 • 177k • 7

pragsri8/ultrafeedback20k_crome-noise20_v3s_preference_datasetsubsampled_plus_original

Viewer • Updated Jul 30, 2025 • 214k • 10

pragsri8/ultrafeedback20k_crome-noise100_v3s_preference_datasetsubsampled_plus_original

Viewer • Updated Jul 30, 2025 • 214k • 7

pragsri8/ultrafeedback20k_crome-noise100_v3s_preference_dataset_plus_original

Viewer • Updated Jul 30, 2025 • 284k • 14

View 54 datasets