nemo_rl.data.datasets.preference_datasets.helpsteer3#
Module Contents#
Classes#
HelpSteer3 preference dataset for DPO training. |
Functions#
API#
- nemo_rl.data.datasets.preference_datasets.helpsteer3.to_preference_data_format(data: dict[str, Any]) dict#
- class nemo_rl.data.datasets.preference_datasets.helpsteer3.HelpSteer3Dataset#
HelpSteer3 preference dataset for DPO training.
Initialization