Skip to content

Direct Preference Optimization (DPO) style rewards#99

Merged
opentaco merged 12 commits intostagingfrom
feature/dpo-rewards
Aug 24, 2023
Merged

Direct Preference Optimization (DPO) style rewards#99
opentaco merged 12 commits intostagingfrom
feature/dpo-rewards

Commits

Commits on Jul 20, 2023

Commits on Jul 21, 2023

Commits on Jul 27, 2023

Commits on Aug 24, 2023