Update README.md

README.md

@@ -70,11 +70,11 @@ You can try the model online (fine-tuned on named entity recognition) using this
 <h3>Quick usage</h3>
 
 ```python
-from transformers import AutoTokenizer, AutoModel
+from transformers import AutoTokenizer, DistilBertForMaskedLM
 from transformers import pipeline
 
 tokenizer = AutoTokenizer.from_pretrained("osiria/blaze-it")
-model = AutoModel.from_pretrained("osiria/blaze-it")
+model = DistilBertForMaskedLM.from_pretrained("osiria/blaze-it")
 pipeline_mlm = pipeline(task="fill-mask", model=model, tokenizer=tokenizer)
 ```