Skip to main content

module aixplain.factories.finetune_factory

Global Variables​

  • prompt_validator

class FinetuneFactory​

A static class for creating and managing the FineTune experience.

Attributes:

  • backend_url (str): The URL for the backend.

classmethod create​

create(
    name: str,
    dataset_list: List[Union[Dataset, str]],
    model: Union[Model, str],
    prompt_template: Optional[str] = None,
    hyperparameters: Optional[Hyperparameters] = None,
    train_percentage: Optional[float] = 100,
    dev_percentage: Optional[float] = 0
) → Finetune

Create a Finetune object with the provided information.

Args:

  • name (Text): Name of the Finetune.
  • dataset_list (List[Dataset]): List of Datasets (or dataset IDs) to be used for fine-tuning.
  • model (Model): Model (Model ID) to be fine-tuned.
  • prompt_template (Text, optional): Fine-tuning prompt_template. Should reference columns in the dataset using format <<COLUMN_NAME>>. Defaults to None.
  • hyperparameters (Hyperparameters, optional): Hyperparameters for fine-tuning. Defaults to None.
  • train_percentage (float, optional): Percentage of training samples. Defaults to 100.
  • dev_percentage (float, optional): Percentage of development samples. Defaults to 0.

Returns:

  • Finetune: The Finetune object created with the provided information or None if there was an error.