update loading instructions

README.md

@@ -52,8 +52,8 @@ Below linear modules (40/193) are fallbacked to fp32 for less than 1% relative a
 ### Load with optimum:
 
 ```python
-from optimum.intel.neural_compressor.quantization import IncQuantizedModelForSeq2SeqLM
-int8_model = IncQuantizedModelForSeq2SeqLM.from_pretrained(
-    'Intel/bart-large-cnn-int8-dynamic',
-)
-```
+from optimum.intel import INCModelForSeq2SeqLM
+
+model_id = "Intel/bart-large-cnn-int8-dynamic"
+int8_model = INCModelForSeq2SeqLM.from_pretrained(model_id)
+```