fix(setup): install either tensorflow-macos or tensorflow depending on platform processor

[btruhand]

Issue #, if available:

I have a M1 Mac and unable to install the dependencies for development using the provided command in the README which is pip install -e ".[test,dev]"

Error gotten:

ERROR: Could not find a version that satisfies the requirement tensorflow<2.11,>=2.4.0; extra == "dev" (from sagemaker-huggingface-inference-toolkit[dev,test]) (from versions: 2.13.0rc0, 2.13.0rc1, 2.13.0rc2, 2.13.0, 2.13.1, 2.14.0rc0, 2.14.0rc1, 2.14.0, 2.14.1, 2.15.0rc0, 2.15.0rc1, 2.15.0, 2.15.1, 2.16.0rc0, 2.16.1)
ERROR: No matching distribution found for tensorflow<2.11,>=2.4.0; extra == "dev"

Python version: 3.9.1

Description of changes:

Found a solution suggested by Apple here where for TF versions <= 2.12 we should install tensorflow-macos instead. Checking sys.platform == "darwin" and platform.processor() == "arm" seems to have fixed the problem for me

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.