Small correction for self-contained code

README.md

@@ -16,7 +16,7 @@ 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 = AutoModelForMaskedLM.from_pretrained('s-sahoo/duo')
 ```
 For a hands-on example, check out this [Colab notebook](https://colab.research.google.com/drive/1Sf7R-dqdR6gq-H8nyZ9E3ZkyvqMTqcwq?usp=sharing).