Update README.md

update model card to use Optimum API instead of using INC API

README.md

@@ -16,7 +16,7 @@ metrics:
 
 ### Post-training static quantization
 
-This is an INT8  PyTorch model quantized with [Intel® Neural Compressor](https://github.com/intel/neural-compressor). 
+This is an INT8  PyTorch model quantized with [huggingface/optimum-intel](https://github.com/huggingface/optimum-intel) through the usage of [Intel® Neural Compressor](https://github.com/intel/neural-compressor).
 
 The original fp32 model comes from the fine-tuned model [Intel/bert-base-uncased-mrpc](https://huggingface.co/Intel/bert-base-uncased-mrpc).
 
@@ -34,8 +34,8 @@ The linear module **bert.encoder.layer.9.output.dense** falls back to fp32 to me
 ### Load with Intel® Neural Compressor:
 
 ```python
-from neural_compressor.utils.load_huggingface import OptimizedModel
-int8_model = OptimizedModel.from_pretrained(
+from optimum.intel.neural_compressor.quantization import IncQuantizedModelForSequenceClassification
+int8_model = IncQuantizedModelForSequenceClassification.from_pretrained(
     'Intel/bert-base-uncased-mrpc-int8-static',
 )
 ```