fix: factor in set instance type when building JumpStart models in ModelBuilder.

[cj-zhang]

Issue #, if available:

• sagemaker/serve integration test fix.

Description of changes:

• When building JumpStart models using ModelBuilder, account for the instance type set on ModelBuilder.
• tests/integ/sagemaker/serve/test_schema_builder.py::test_model_builder_happy_path_with_task_provided_remote_schema_mode[google-bert/bert-base-cased-fill-mask-ml.m5.xlarge] and [google-bert/bert-base-uncased] were failing because the packaged image URI with bert is a GPU image, but the test uses a CPU instance type.

ModelBuilder logs showing instance type is not accounted for:

2025-03-18T08:04:19.0260513Z No instance type selected for inference hosting endpoint. Defaulting to ml.p3.2xlarge.
2025-03-18T08:04:19.0262371Z ModelBuilder: INFO:     JumpStart ID huggingface-tc-bert-base-cased is packaged with Image URI: 763104351884.dkr.ecr.us-west-2.amazonaws.com/huggingface-pytorch-inference:2.3.0-transformers4.48.0-gpu-py311-cu121-ubuntu22.04

Endpoint Deployment fails due to:
Invalid combination: instance m5 and Cuda 12.2. Please provide a supported configuration for this region.

Testing done: integ tests succeed locally.

Merge Checklist

Put an x in the boxes that apply. You can also fill these out after creating the PR. If you're unsure about any of them, don't hesitate to ask. We're here to help! This is simply a reminder of what we are going to look for before merging your pull request.

General

• I have read the CONTRIBUTING doc
• I certify that the changes I am introducing will be backward compatible, and I have discussed concerns about this, if any, with the Python SDK team
• I used the commit message format described in CONTRIBUTING
• I have passed the region in to all S3 and STS clients that I've initialized as part of this change.
• I have updated any necessary documentation, including READMEs and API docs (if appropriate)

Tests

• I have added tests that prove my fix is effective or that my feature works (if appropriate)
• I have added unit and/or integration tests as appropriate to ensure backward compatibility of the changes
• I have checked that my tests are not configured for a specific region or account (if appropriate)
• I have used unique_name_from_base to create resource names in integ tests (if appropriate)
• If adding any dependency in requirements.txt files, I have spell checked and ensured they exist in PyPi

By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.

[gwang111]

Lgtm