fix the code sample

README.md

@@ -15,9 +15,9 @@ To use the pre-trained model for masked language modeling, use the following sni
 from transformers import AutoModelForMaskedLM, AutoTokenizer
 
 # See the `MDLM` collection page on the hub for list of available models.
-tokenizer = transformers.AutoTokenizer.from_pretrained('gpt2')
+tokenizer = AutoTokenizer.from_pretrained('gpt2')
 model_name = 'kuleshov-group/mdlm-owt'
-model = AutoModelForMaskedLM.from_pretrained(model_name)
+model = AutoModelForMaskedLM.from_pretrained(model_name, trust_remote_code=True)
 ```
 
 For more details, please see our github repository: [MDLM](https://github.com/kuleshov-group/mdlm)