update loading instructions

README.md

@@ -35,10 +35,10 @@ The linear module **bert.encoder.layer.6.attention.self.key** falls back to fp32
 #### Load with optimum:
 
 ```python
-from optimum.intel.neural_compressor.quantization import IncQuantizedModelForSequenceClassification 
-int8_model = IncQuantizedModelForSequenceClassification(
-    'Intel/MiniLM-L12-H384-uncased-mrpc-int8-static',
-)
+from optimum.intel import INCModelForSequenceClassification 
+
+model_id = "Intel/MiniLM-L12-H384-uncased-mrpc-int8-static"
+int8_model = INCModelForSequenceClassification(model_id)
 ```
 
 ### ONNX
@@ -62,4 +62,4 @@ The calibration dataloader is the eval dataloader. The calibration sampling size
 ```python
 from optimum.onnxruntime import ORTModelForSequenceClassification
 model = ORTModelForSequenceClassification.from_pretrained('Intel/MiniLM-L12-H384-uncased-mrpc-int8-static')
-```
+```