Model.deploy() returning None instead of predictor/endpoint object #4619

Describe the bug
A clear and concise description of what the bug is.

from sagemaker.model import Model
from sagemaker.predictor import Predictor

instance_type, instance_count = "ml.m5.xlarge", 1

predictor = model.deploy(
    initial_instance_count=instance_count,
    instance_type=instance_type,
    predictor_cls=Predictor
)

Above code snippet from this article returns None for predictor instead of the endpoint object.

To reproduce
A clear, step-by-step set of instructions to reproduce the bug.
The provided code need to be complete and runnable, if additional data is needed, please include them in the issue.

Expected behavior
A clear and concise description of what you expected to happen.

Endpoint object per the article linked above, that can be used to invoke and delete the endpoint.

Screenshots or logs
If applicable, add screenshots or logs to help explain your problem.

System information
A description of your system. Please provide:

• SageMaker Python SDK version: 2.216.1
• Framework name (eg. PyTorch) or algorithm (eg. KMeans): Not sure
• Framework version: NA
• Python version: 3.9.6
• CPU or GPU: NA (using Sagemaker Jumpstart, instance_type="ml.m5.xlarge")
• Custom Docker image (Y/N): N

Additional context
Add any other context about the problem here.

Trying to test with the following jumpstart model:
model_id, model_version = "huggingface-spc-bert-base-cased", "1.0.0"