Update model card

README.md

@@ -49,8 +49,8 @@ The linear modules **albert.encoder.albert_layer_groups.0.albert_layers.0.ffn_ou
 ### Load with Intel® Neural Compressor:
 
 ```python
-from neural_compressor.utils.load_huggingface import OptimizedModel
-int8_model = OptimizedModel.from_pretrained(
-    'Intel/albert-base-v2-sst2-int8-static',
-)
+from optimum.intel.neural_compressor import IncQuantizedModelForSequenceClassification
+
+model_id = "Intel/albert-base-v2-sst2-int8-static"
+int8_model = IncQuantizedModelForSequenceClassification.from_pretrained(model_id)
 ```