Update model card

README.md

@@ -47,8 +47,8 @@ The linear module **roberta.encoder.layer.6.attention.self.query** falls back to
 ### Load with Intel® Neural Compressor:
 
 ```python
-from neural_compressor.utils.load_huggingface import OptimizedModel
-int8_model = OptimizedModel.from_pretrained(
-    'Intel/camembert-base-mrpc-int8-dynamic',
-)
+from optimum.intel.neural_compressor import IncQuantizedModelForSequenceClassification
+
+model_id = "Intel/camembert-base-mrpc-int8-dynamic"
+int8_model = IncQuantizedModelForSequenceClassification.from_pretrained(model_id)
 ```