lmflow.pipeline.rm_tuner#

Attributes#

logger

Classes#

RewardModelTuner

Initializes the RewardModelTuner class.

Module Contents#

lmflow.pipeline.rm_tuner.logger[source]#
class lmflow.pipeline.rm_tuner.RewardModelTuner(model_args, data_args, finetuner_args, *args, **kwargs)[source]#

Bases: lmflow.pipeline.finetuner.Finetuner

Initializes the RewardModelTuner class.

Parameters:

  • model_args (ModelArguments object.) – Contains the arguments required to load the model.

  • data_args (DatasetArguments object.) – Contains the arguments required to load the dataset.

  • finetuner_args (RewardModelTunerArguments object.) – Contains the arguments required to perform finetuning.

  • args (Optional.) – Positional arguments.

  • kwargs (Optional.) – Keyword arguments.

tune(model: lmflow.models.hf_text_regression_model.HFTextRegressionModel, dataset, transform_dataset_in_place=True, data_collator=None, **kwargs)[source]#