diff --git a/src/axolotl/core/trainer_builder/rl.py b/src/axolotl/core/trainer_builder/rl.py index f62e14880..e36af0f71 100644 --- a/src/axolotl/core/trainer_builder/rl.py +++ b/src/axolotl/core/trainer_builder/rl.py @@ -247,4 +247,4 @@ class HFPPOTrainerBuilder(TrainerBuilderBase): def build(self, total_num_steps): # build PPOConfig - pass + raise NotImplementedError("PPO trainer builder is not implemented yet.")