I have a trained model in .joblib format and prior to dumping it to an S3 folder, I’m compressing the file using python’s tarfile library. Thereafter, I want to create a SageMaker endpoint using that given file. However, I get errors
Failed to extract model data archive from URL "s3://***/models/TitanicPredictor/TitanicPredictor_20240528_151259.tar.gz". Please ensure that the object located at the URL is a valid tar.gz archive.
However, I see that the file is definitely there and looks to be under the right file type.
I fear the issue is that I’m not using the built-in Estimator functionality that Sagemaker provides. Generally I wanted to avoid using Estimator as I feel it doesn’t give much freedom to the developer to express the ideas in a more flexible way. Any ideas on what I might be doing wrong?