def decode_tuned_model()

in google/generativeai/types/model_types.py [0:0]

• 32 lines of code
• 8 McCabe index (conditional complexity)

def decode_tuned_model(tuned_model: protos.TunedModel | dict["str", Any]) -> TunedModel:
    if isinstance(tuned_model, protos.TunedModel):
        tuned_model = type(tuned_model).to_dict(
            tuned_model, including_default_value_fields=False
        )  # pytype: disable=attribute-error
    tuned_model["state"] = to_tuned_model_state(tuned_model.pop("state", None))

    base_model = tuned_model.pop("base_model", None)
    tuned_model_source = tuned_model.pop("tuned_model_source", None)
    if base_model is not None:
        tuned_model["base_model"] = base_model
        tuned_model["source_model"] = base_model
    elif tuned_model_source is not None:
        tuned_model["base_model"] = tuned_model_source["base_model"]
        tuned_model["source_model"] = tuned_model_source["tuned_model"]

    idecode_time(tuned_model, "create_time")
    idecode_time(tuned_model, "update_time")

    task = tuned_model.pop("tuning_task", None)
    if task is not None:
        hype = task.pop("hyperparameters", None)
        if hype is not None:
            hype = Hyperparameters(**hype)
            task["hyperparameters"] = hype

        idecode_time(task, "start_time")
        idecode_time(task, "complete_time")

        snapshots = task.pop("snapshots", None)
        if snapshots is not None:
            for snap in snapshots:
                idecode_time(snap, "compute_time")
            task["snapshots"] = snapshots
        task = TuningTask(**task)
        tuned_model["tuning_task"] = task
    return TunedModel(**tuned_model)