update loading instructions

README.md

@@ -36,9 +36,9 @@ tags:
 To load the quantized model, you can do as follows:
 
 ```python
-from optimum.intel.neural_compressor.quantization import IncQuantizedModelForSequenceClassification
+from optimum.intel import INCModelForSequenceClassification
 
-model = IncQuantizedModelForSequenceClassification.from_pretrained("Intel/albert-base-v2-MRPC-int8")
+model = INCModelForSequenceClassification.from_pretrained("Intel/albert-base-v2-MRPC-int8")
 ```
 
 #### Test result
@@ -46,4 +46,4 @@ model = IncQuantizedModelForSequenceClassification.from_pretrained("Intel/albert
 |   |INT8|FP32|
 |---|:---:|:---:|
 | **Accuracy (eval-f1)** |0.9193|0.9263|
-| **Model size (MB)**  |45.0|46.7|
+| **Model size (MB)**  |45.0|46.7|