diff --git a/apps/accelerate/chatllama/README.md b/apps/accelerate/chatllama/README.md index c16ce3df..5e2f63ca 100644 --- a/apps/accelerate/chatllama/README.md +++ b/apps/accelerate/chatllama/README.md @@ -34,7 +34,7 @@ from chatllama.rlhf.config import Config path = "path_to_config_file.yaml" config = Config(path=path) trainer = RLTrainer(config.trainer) -trainer.distillate() +trainer.distill() trainer.train() trainer.training_stats.plot() ``` diff --git a/apps/accelerate/chatllama/chatllama/rlhf/reward.py b/apps/accelerate/chatllama/chatllama/rlhf/reward.py index abf15c5d..eb2dcacd 100644 --- a/apps/accelerate/chatllama/chatllama/rlhf/reward.py +++ b/apps/accelerate/chatllama/chatllama/rlhf/reward.py @@ -258,7 +258,7 @@ class RewardTrainer: train: Train the reward model generate_user_input: Generate the user input for the LLM to evaluate a couple, (user_input, completion) and assing a score - distillate: Parse the dataset and assign scores using LLMs + distill: Parse the dataset and assign scores using LLMs """ def __init__(self, config: ConfigReward) -> None: @@ -324,7 +324,7 @@ def __init__(self, config: ConfigReward) -> None: config=self.config.deepspeed_config_path, ) - def distillate( + def distill( self, ): """Parse the dataset and assign scores using LLMs