pragsri8/PM_gemma2-9b_ultrafeedback20kvanilla_lam1_loss-type_custom_logprob_with_neutrals_lamda_lr1e-6_v1 Feature Extraction • 9B • Updated 22 days ago • 110
pragsri8/PM_gemma2-9b_ultrafeedback_usual_up-deg_plus_att-ranked_logprob_with_neutrals_lamda_lr1e-6 Feature Extraction • 9B • Updated Jul 13 • 10
pragsri8/PM_gemma2-9b_ultrafeedback_synthqrand_lam1_loss_custom_logprob_with_neutrals_lamda_lr1e-6_v1 Feature Extraction • 9B • Updated Jul 7 • 10
pragsri8/PM_gemma2-9b_ultrafeedback_synthonly_lam1_loss_custom_logprob_with_neutrals_lamda_lr1e-6_v1 Feature Extraction • 9B • Updated Jul 7 • 11
pragsri8/PM_gemma2-9b_ultrafeedback_attimp_lamda_1_loss-type_custom_logprob_with_neutrals_lamda_lr1e-6 Feature Extraction • 9B • Updated Jul 7 • 14
pragsri8/ultrafeedback20k_crome-noise100_v3s_preference_dataset Viewer • Updated 15 days ago • 373k • 145
pragsri8/ultrafeedback20k_crome-noise20_v3s_preference_datasetsubsampled_plus_original Viewer • Updated 22 days ago • 214k • 86
pragsri8/ultrafeedback20k_crome-noise100_v3s_preference_datasetsubsampled_plus_original Viewer • Updated 22 days ago • 214k • 89
pragsri8/ultrafeedback20k_crome-noise100_v3s_preference_dataset_plus_original Viewer • Updated 22 days ago • 284k • 97
pragsri8/ultrafeedback20k_crome-noise20_v3s_preference_dataset_plus_original Viewer • Updated 22 days ago • 289k • 87
pragsri8/ultrafeedback20k_crome-noise100_v3s_preference_dataset_prob_A_filtered0.2 Viewer • Updated 22 days ago • 264k • 99
pragsri8/ultrafeedback20k_crome-noise20_v3s_preference_dataset_prob_A_filtered0.2 Viewer • Updated 22 days ago • 269k • 94