stack_exchange_paired_dataset

torchtune.datasets.stack_exchange_paired_dataset(tokenizer: ModelTokenizer, *, source: str = 'lvwerra/stack-exchange-paired', column_map: Optional[Dict[str, str]] = None, train_on_input: bool = False, filter_fn: Optional[Callable] = None, split: str = 'train', **load_dataset_kwargs: Dict[str, Any]) → PreferenceDataset

Family of preference datasets similar to the Stack Exchange Paired dataset.

It is recommended to configure the tokenizer with the QuestionAnswerTemplate in conjunction with this dataset.

Parameters:

• tokenizer (ModelTokenizer) – Tokenizer used by the model that implements the tokenize_messages method.

• source (str) – path to dataset repository on Hugging Face. For local datasets, define source as the data file type (e.g. “json”, “csv”, “text”) and pass in the filepath in data_files. See Hugging Face’s load_dataset for more details. Default is lvwerra/stack-exchange-paired.

• column_map (Optional[Dict[str, str]]) – a mapping to change the expected “prompt”, “chosen”, and “rejected” column names to the actual column names in the dataset. Keys should be “prompt”, “chosen”, and “rejected” and values should be the actual column names. Default is None, keeping the default column names.

• train_on_input (bool) – Whether the model is trained on the prompt or not. Default is False.

• filter_fn (Optional[Callable]) – callable used to filter the dataset prior to any pre-processing. See the Hugging Face docs for more details.

• split (str) – split argument for datasets.load_dataset. You can use this argument to load a subset of a given split, e.g. split="train[:10%]". Default is “train”.

• **load_dataset_kwargs (Dict[str, Any]) – additional keyword arguments to pass to load_dataset.

Returns:

The preference dataset built from source paired data.

Return type:

PreferenceDataset