Added exception for warning caused while creating int4 tensor

[hthadicherla]

What does this PR do?

Type of change: Bug Fix

Overview: This PR adds an exception for error warning raised while creating graph surgeon quantized weight tensors and in case of int4 quantization for newer version of onnx 1.19. This can be done because we have implemented the fix for this in #423 where we are converting values from ml_dtypes.int4 (ONNX 1.19 format for exporting and importing int4 weight tensors in and out of onnx model) to np.int8(ONNX 1.18 format) when we are packing and unpacking the weights in datatype.

Error caused:
[modelopt][onnx] - ERROR - Trying to create tensor with incompatible types: int8, 22
where 22 is representation of ml_dtypes int4

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 73.38%. Comparing base (41de55f) to head (948478c).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #461      +/-   ##
==========================================
- Coverage   73.38%   73.38%   -0.01%     
==========================================
  Files         180      180              
  Lines       18110    18111       +1     
==========================================
  Hits        13290    13290              
- Misses       4820     4821       +1     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.