Issue when following GPT-J 6B blog post instructions

Trying to spin up a GPT-J 6B on AWS per this blog post by Philipp Schmid.
AWS account in Frankfurt gets this error message even though I’m using AdminAccess and the trust relationship is set up:

An error occurred (ValidationException) when calling the CreateModel operation: Could not access model data at s3://huggingface-sagemaker-models/transformers/4.12.3/pytorch/1.9.1/gpt-j/model.tar.gz. Please ensure that the role “arn:aws:iam::387783137047:role/service-role/SageMaker-datascientist” exists and that its trust relationship policy allows the action “sts:AssumeRole” for the service principal “”. Also ensure that the role has “s3:GetObject” permissions and that the object is located in eu-central-1.

Any pointers would be appreciated.

You must be in us-east-1. For me, on my local, I edited ~/.aws/config and changed my [default] region to us-east-1.

That simple??? Thank you!