causal reward modeling

Team

university

https://docs.google.com/document/u/0/?tgif=d

AI & ML interests

None defined yet.

causal-rewards 's datasets 4

causal-rewards/sycophancy_dpo_llama3.1_8b_ultrachat200k_iter1_new

Viewer • Updated Sep 21 • 847 • 19

causal-rewards/ultrafeedback_60658_pref_dataset_original_plus_filtered_improved_degraded_attimp_threshold0p2

Viewer • Updated Jul 3 • 920k • 17

causal-rewards/ultrafeedback_60658_preference_dataset_original_neutrals_filtered_improve-degrade_filtered0p2

Viewer • Updated Apr 22 • 218k • 9

causal-rewards/ultrafeedback-binarized-preferences-cleaned-neutral

Viewer • Updated Apr 16 • 60.9k • 13