Python 如何将参数传递给Sagemaker预测端点？

我想将参数传递给Sagemaker预测端点。具体来说，我想传入s3中的目录，从中下载一个模型文件。这就是我现在部署模型的方式，但我不相信有任何参数可供我传入参数

import sagemaker
from sagemaker.pytorch import PyTorchModel
from sagemaker.serializers import JSONSerializer
from sagemaker.deserializers import JSONDeserializer


pytorch_predictor = PyTorchModel(
                                model_data=model_data,
                                role=role,
                                entry_point=entry_point,
                                source_dir=source_dir,
                                image_uri=image_uri,
                                framework_version='1.3.1',
                                py_version='py3'
                                )
predictor = pytorch_predictor.deploy(
                                    initial_instance_count=1,
                                    instance_type=instance_type,
                                    accelerator_type=accelerator_type,
                                    serializer=JSONSerializer(),
                                    deserializer=JSONDeserializer()
                                    )

这是我的入门脚本：

def model_fn(model_dir):
    #loading model - ideally, I could pass in an argument here to download a model file from s3

def input_fn(request_body, request_content_type):
    #process input

# inference
def predict_fn(input_object, model):
    #inference

# postprocess
def output_fn(predictions, content_type):
    #postprocess