nemo_rl.data.datasets.preference_datasets.helpsteer3#

Module Contents#

Classes#

HelpSteer3Dataset

HelpSteer3 preference dataset for DPO training.

Functions#

API#

nemo_rl.data.datasets.preference_datasets.helpsteer3.to_preference_data_format(
data: dict[str, Any],
) dict[str, list[dict[str, int | list[dict[str, str | Any]]]] | list[dict[str, str]]]#
class nemo_rl.data.datasets.preference_datasets.helpsteer3.HelpSteer3Dataset#

HelpSteer3 preference dataset for DPO training.

Initialization