Fix large model check in Intel's Neural Compressor (#27746)
### Description
This PR updates the logic for identifying a large model in Intel's
Neural Compressor.
### Motivation and Context
The original logic was not sufficient to detect whether a model produced
by the model builder is too large or not. Here is an example traceback
from an internal customer.
```
Traceback (most recent call last):
File "D:\a\_work\1\s\edge.onnxruntime-genai\src\python\py\models\builder.py", line 502, in <module>
create_model(
File "C:\ToolCache\Python\3.12.10\x64\Lib\site-packages\torch\utils\_contextlib.py", line 124, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "D:\a\_work\1\s\edge.onnxruntime-genai\src\python\py\models\builder.py", line 346, in create_model
onnx_model.save_model(output_dir)
File "D:\a\_work\1\s\edge.onnxruntime-genai\src\python\py\models\builders\base.py", line 748, in save_model
model = self.to_int4()
^^^^^^^^^^^^^^
File "D:\a\_work\1\s\edge.onnxruntime-genai\src\python\py\models\builders\base.py", line 738, in to_int4
quant.process()
File "C:\ToolCache\Python\3.12.10\x64\Lib\site-packages\onnxruntime\quantization\matmul_nbits_quantizer.py", line 1442, in process
self.int4_quant_algo()
File "C:\ToolCache\Python\3.12.10\x64\Lib\site-packages\onnxruntime\quantization\matmul_nbits_quantizer.py", line 1388, in int4_quant_algo
self.model = rtn_quantize(
^^^^^^^^^^^^^
File "C:\ToolCache\Python\3.12.10\x64\Lib\site-packages\onnxruntime\quantization\neural_compressor\weight_only.py", line 456, in rtn_quantize
model = ONNXModel(model)
^^^^^^^^^^^^^^^^
File "C:\ToolCache\Python\3.12.10\x64\Lib\site-packages\onnxruntime\quantization\neural_compressor\onnx_model.py", line 52, in __init__
self.check_is_large_model()
File "C:\ToolCache\Python\3.12.10\x64\Lib\site-packages\onnxruntime\quantization\neural_compressor\onnx_model.py", line 91, in check_is_large_model
raise e
File "C:\ToolCache\Python\3.12.10\x64\Lib\site-packages\onnxruntime\quantization\neural_compressor\onnx_model.py", line 84, in check_is_large_model
init_bytes = init.SerializeToString()
^^^^^^^^^^^^^^^^^^^^^^^^
google.protobuf.message.EncodeError: Failed to serialize proto
```
