Update README.md

README.md

@@ -14,8 +14,8 @@ large batch size of 0.5M tokens. A larger 762 million parameter model can also b
 
 ```python
 from transformers import AutoTokenizer,AutoModel
-model = AutoModel.from_pretrained("mmukh/SOBertBase")
-tokenizer = AutoTokenizer.from_pretrained("mmukh/SOBertBase")
+model = MegatronBertModel.from_pretrained("mmukh/SOBertBase")
+tokenizer = BertTokenizerFast.from_pretrained("mmukh/SOBertBase")
 
 ```