Pragya Srivastava's picture

1 2 3

Pragya Srivastava

pragsri8

·

AI & ML interests

None yet

Recent Activity

updated a model 28 days ago

pragsri8/Llama-3.2-3B-Instruct_PairPM_helpsteer_v1

published a model 28 days ago

pragsri8/Llama-3.2-3B-Instruct_PairPM_helpsteer_v1

published a model 29 days ago

pragsri8/Llama-3.2-3B-Instruct_helpsteer_v1

View all activity

Organizations

pragsri8 's models 24

pragsri8/Llama-3.2-3B-Instruct_PairPM_helpsteer_v1

Text Generation • 3B • Updated 28 days ago • 145

pragsri8/Llama-3.2-3B-Instruct_helpsteer_v1

Updated 29 days ago

pragsri8/gemma2-9b_skyworks_lamda_1_loss-type_custom_logprob_with_neutrals_lamda_lr1e-6_v1

Text Generation • 9B • Updated about 1 month ago • 4

pragsri8/gemma2-9b_skyworks_20k_rrm_filtered0p2thresh_plus_original_lr1e-6_v1

Text Generation • 9B • Updated about 1 month ago • 6

pragsri8/gemma2-9b_skyworks_crome_augmentations_filtered0p2thresh_plus_original_lamda_lr1e-6_v1

Text Generation • 9B • Updated about 1 month ago • 6

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

pragsri8/PM_gemma2-9b_ultrafeedback20kvanilla_lam1_loss-type_custom_logprob_with_neutrals_lamda_lr1e-6_v1

Feature Extraction • 9B • Updated Jul 30 • 7

pragsri8/PM_gemma2-9b_ultrafeedback-dpo-iter2

Feature Extraction • 9B • Updated Jul 29 • 6

pragsri8/ODIN_gemma2-9b_ultrafeedback

Feature Extraction • 9B • Updated Jul 27 • 4

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

Feature Extraction • 9B • Updated Jul 13 • 6

pragsri8/PM_gemma2-9b_ultrafeedback_synthqrand_lam1_loss_custom_logprob_with_neutrals_lamda_lr1e-6_v1

Feature Extraction • 9B • Updated Jul 7 • 6

pragsri8/PM_gemma2-9b_ultrafeedback_synthonly_lam1_loss_custom_logprob_with_neutrals_lamda_lr1e-6_v1

Feature Extraction • 9B • Updated Jul 7 • 6

pragsri8/PM_gemma2-9b_ultrafeedback_attimp_lamda_1_loss-type_custom_logprob_with_neutrals_lamda_lr1e-6

Feature Extraction • 9B • Updated Jul 7 • 6

pragsri8/Llama-3.1-8B-Instruct-GenRM-Reproduce

pragsri8/llama-3.1-8b-sft-full_noisy_2.0_bon-sft

Text Generation • 8B • Updated Apr 11 • 6

pragsri8/llama-3.1-8b-sft-full_noisy_1.0_bon-sft

Text Generation • 8B • Updated Apr 10 • 8

pragsri8/llama-3.1-8b-sft-full_noisy_0.5_bon-sft

Text Generation • 8B • Updated Apr 10 • 8

pragsri8/llama-3.1-8b-sft-full_vanilla_bon-sft

Text Generation • 8B • Updated Apr 10 • 11

pragsri8/math_sft

Updated Nov 21, 2024

pragsri8/llama-3.2-1B-RM-Ultrafeedback

Updated Nov 3, 2024

pragsri8/llama70b_finetuned

Updated Oct 1, 2024

pragsri8/dpo_offline_20k

Updated Jul 20, 2024

pragsri8/phi2_hh-rlhf_sft

Updated Jul 16, 2024

pragsri8/phi-1_5_rm-gpt2_100

Updated Jun 18, 2024