Fix loading instructions

README.md

@@ -30,10 +30,10 @@ The original fp32 model comes from the fine-tuned model [Intel/bert-base-uncased
 ### Load with optimum:
 
 ```python
-from optimum.intel.neural_compressor.quantization import IncQuantizedModelForSequenceClassification 
-int8_model = IncQuantizedModelForSequenceClassification(
-    'Intel/bert-base-uncased-mrpc-int8-qat',
-)
+from optimum.intel import INCModelForSequenceClassification
+
+model_id = "Intel/bert-base-uncased-mrpc-int8-qat"
+int8_model = INCModelForSequenceClassification.from_pretrained(model_id)
 ```
 
 ### Training hyperparameters