Update README.md

README.md

@@ -26,8 +26,10 @@ In particular, for training the model we used a batch size of 256, Adam optimize
 # Usage
 
 
-## Use a pipeline as a high-level helper from the transformers import pipeline
+## Use a pipeline as a high-level
 ```
+from transformers import pipeline
+
 pipe = pipeline("fill-mask", model="citiusLTL/DisorBERT")
 ```
 ## Load model directly