nemo_rl.data.datasets.preference_datasets.tulu3#
Module Contents#
Classes#
Tulu3 preference dataset for DPO training. |
API#
- class nemo_rl.data.datasets.preference_datasets.tulu3.Tulu3PreferenceDataset(**kwargs)#
Bases:
nemo_rl.data.datasets.raw_dataset.RawDatasetTulu3 preference dataset for DPO training.
Initialization
- format_data(data: dict[str, Any]) dict[str, Any]#