Fix weight loading of large model in INC quantzation pass (#857)

## Describe your changes

Fix weight loading of large model in inc quantzation pass. Reload weight
for model > 2GB to prevent missing weight files.

## Checklist before requesting a review
- [ ] Add unit tests for this change.
- [ ] Make sure all tests can pass.
- [ ] Update documents if necessary.
- [ ] Lint and apply fixes to your code by running `lintrunner -a`
- [ ] Is this a user-facing change? If yes, give a description of this
change to be included in the release notes.

## (Optional) Issue link

#852

---------

Signed-off-by: yuwenzho <[email protected]>

olive/passes/onnx/inc_quantization.py

@@ -562,6 +562,13 @@ def _run_for_config(
  "find any quantized model which meet accuracy goal. "
  "Try to increase 'max_trials' in 'tuning_criterion'."
  )
+
+ # reload weight for model with size > 2GB to prevent error of missing weight files
+ if q_model.is_large_model:
+ from onnx.external_data_helper import load_external_data_for_model
+
+ load_external_data_for_model(q_model.model, os.path.dirname(q_model._model_path))
+
  # save the model to the output path and return the model
  return model_proto_to_olive_model(q_model.model, output_model_path, config)