Update README.md

README.md

@@ -17,9 +17,9 @@ large batch size of 0.5M tokens. A smaller 109 million parameter model can also
 #### How to use
 
 ```python
-from transformers import AutoTokenizer,AutoModel
-model = AutoModel.from_pretrained("mmukh/SOBertLarge")
-tokenizer = AutoTokenizer.from_pretrained("mmukh/SOBertLarge")
+from transformers import MegatronBertModel,BertTokenizerFast
+model = MegatronBertModel.from_pretrained("mmukh/SOBertLarge")
+tokenizer = BertTokenizerFast.from_pretrained("mmukh/SOBertLarge")
 
 ```