download_model.py

from sagemaker.s3 import S3Downloader

S3Downloader.download(
    s3_uri=huggingface_estimator.model_data, # s3 uri where the trained model is located
    local_path='.', # local path where *.targ.gz is saved
    sagemaker_session=sess # sagemaker session used for training the model
)