Hey! Does anyone know if it is possible to use a service class as a template to deploy multiple (mlflow stored) models by varying the mlflow model name? Currently this is my code:

from typing import Dict, List, Optional

import bentoml
import mlflow
import pandas as pd

MLFLOW_MODEL_NAME = "iforest-test:latest"  # TODO: Take this as a parameter


# TODO: Generalize to anomaly detection service
@bentoml.service(resources={"cpu": "200m", "memory": "512Mi"})
class AnomalyDetectionService:
    anomaly_detection_model = bentoml.mlflow.get(MLFLOW_MODEL_NAME)

    def __init__(self):
        mlflow_model_path = self.anomaly_detection_model.path_of(
            bentoml.mlflow.MLFLOW_MODEL_FOLDER
        )
        print(mlflow_model_path)
        self.model = mlflow.pyfunc.load_model(mlflow_model_path)

    @bentoml.api
    def predict(
        self,
        X: pd.DataFrame,
        params: Optional[Dict[str, str]] = {"threshold": "threshold_q95"},
    ) -> pd.DataFrame:
        return self.model.predict(X, params=params)