update loading instructions

README.md

@@ -47,10 +47,10 @@ The original fp32 model comes from the fine-tuned model [bart-large-mrpc](https:
 #### Load with optimum:
 
 ```python
-from optimum.intel.neural_compressor.quantization import IncQuantizedModelForSequenceClassification
-int8_model = IncQuantizedModelForSequenceClassification.from_pretrained(
-    'Intel/bart-large-mrpc-int8-dynamic',
-)
+from optimum.intel import INCModelForSequenceClassification
+
+model_id = "Intel/bart-large-mrpc-int8-dynamic"
+int8_model = INCModelForSequenceClassification.from_pretrained(model_id)
 ```
 
 ### ONNX
@@ -72,4 +72,4 @@ The original fp32 model comes from the fine-tuned model [bart-large-mrpc](https:
 ```python
 from optimum.onnxruntime import ORTModelForSequenceClassification
 model = ORTModelForSequenceClassification.from_pretrained('Intel/bart-large-mrpc-int8-dynamic')
-```
+```