Fix import (#159)

Author: echarlaix

README.md

@@ -95,7 +95,7 @@ In this example, we've quantized a model from the Hugging Face Hub, but it could
 ```python
 from functools import partial
 from datasets import Dataset
-from optimum.onnxruntime import ORTModel
+from optimum.onnxruntime.model import ORTModel
 
 # Load quantized model
 ort_model = ORTModel("model-quantized.onnx", quantizer._onnx_config)

examples/onnxruntime/optimization/question-answering/run_qa.py

@@ -34,8 +34,8 @@
 from transformers.utils import check_min_version
 from transformers.utils.versions import require_version
 
-from optimum.onnxruntime import ORTModel
 from optimum.onnxruntime.configuration import OptimizationConfig, ORTConfig
+from optimum.onnxruntime.model import ORTModel
 from optimum.onnxruntime.optimization import ORTOptimizer
 from trainer_qa import QuestionAnsweringTrainer
 from utils_qa import postprocess_qa_predictions

examples/onnxruntime/optimization/text-classification/run_glue.py

@@ -34,8 +34,8 @@
 from transformers.utils import check_min_version
 from transformers.utils.versions import require_version
 
-from optimum.onnxruntime import ORTModel
 from optimum.onnxruntime.configuration import OptimizationConfig, ORTConfig
+from optimum.onnxruntime.model import ORTModel
 from optimum.onnxruntime.optimization import ORTOptimizer
 
 

examples/onnxruntime/optimization/token-classification/run_ner.py

@@ -35,8 +35,8 @@
 from transformers.utils import check_min_version
 from transformers.utils.versions import require_version
 
-from optimum.onnxruntime import ORTModel
 from optimum.onnxruntime.configuration import OptimizationConfig, ORTConfig
+from optimum.onnxruntime.model import ORTModel
 from optimum.onnxruntime.optimization import ORTOptimizer
 
 

examples/onnxruntime/quantization/question-answering/run_qa.py

@@ -35,8 +35,9 @@
 from transformers.utils.versions import require_version
 
 from onnxruntime.quantization import QuantFormat, QuantizationMode, QuantType
-from optimum.onnxruntime import ORTModel, ORTQuantizer
+from optimum.onnxruntime import ORTQuantizer
 from optimum.onnxruntime.configuration import AutoCalibrationConfig, ORTConfig, QuantizationConfig
+from optimum.onnxruntime.model import ORTModel
 from optimum.onnxruntime.preprocessors import QuantizationPreprocessor
 from optimum.onnxruntime.preprocessors.passes import (
     ExcludeGeLUNodes,

examples/onnxruntime/quantization/text-classification/run_glue.py

@@ -35,8 +35,9 @@
 from transformers.utils.versions import require_version
 
 from onnxruntime.quantization import QuantFormat, QuantizationMode, QuantType
-from optimum.onnxruntime import ORTModel, ORTQuantizer
+from optimum.onnxruntime import ORTQuantizer
 from optimum.onnxruntime.configuration import AutoCalibrationConfig, ORTConfig, QuantizationConfig
+from optimum.onnxruntime.model import ORTModel
 from optimum.onnxruntime.preprocessors import QuantizationPreprocessor
 from optimum.onnxruntime.preprocessors.passes import (
     ExcludeGeLUNodes,

examples/onnxruntime/quantization/token-classification/run_ner.py

@@ -36,8 +36,9 @@
 from transformers.utils.versions import require_version
 
 from onnxruntime.quantization import QuantFormat, QuantizationMode, QuantType
-from optimum.onnxruntime import ORTModel, ORTQuantizer
+from optimum.onnxruntime import ORTQuantizer
 from optimum.onnxruntime.configuration import AutoCalibrationConfig, ORTConfig, QuantizationConfig
+from optimum.onnxruntime.model import ORTModel
 from optimum.onnxruntime.preprocessors import QuantizationPreprocessor
 from optimum.onnxruntime.preprocessors.passes import (
     ExcludeGeLUNodes,

tests/onnxruntime/test_onnxruntime.py

@@ -23,7 +23,7 @@
 from transformers.onnx import validate_model_outputs
 
 from onnxruntime.quantization import QuantFormat, QuantizationMode, QuantType
-from optimum.onnxruntime import ORTConfig, ORTModel, ORTOptimizer, ORTQuantizableOperator, ORTQuantizer
+from optimum.onnxruntime import ORTConfig, ORTOptimizer, ORTQuantizableOperator, ORTQuantizer
 from optimum.onnxruntime.configuration import (
     AutoCalibrationConfig,
     AutoQuantizationConfig,