nemo_rl.data.hf_datasets.helpsteer3#

Module Contents#

Classes#

HelpSteer3Dataset

HelpSteer3 preference dataset for DPO training.

Functions#

API#

nemo_rl.data.hf_datasets.helpsteer3.format_helpsteer3(
data: dict[str, Any],
) dict[str, str | dict[str, str]]#
class nemo_rl.data.hf_datasets.helpsteer3.HelpSteer3Dataset#

HelpSteer3 preference dataset for DPO training.

Initialization