Update README.md

README.md

@@ -13,9 +13,9 @@ large batch size of 0.5M tokens. A larger 762 million parameter model can also b
 #### How to use
 
 ```python
-from transformers import MegatronBertModel,BertTokenizerFast
+from transformers import MegatronBertModel,PreTrainedTokenizerFast
 model = MegatronBertModel.from_pretrained("mmukh/SOBertBase")
-tokenizer = BertTokenizerFast.from_pretrained("mmukh/SOBertBase")
+tokenizer = PreTrainedTokenizerFast.from_pretrained("mmukh/SOBertBase")
 
 ```