Update README.md

README.md

@@ -12,8 +12,8 @@ We limited the statement itself to 100 tokens and the context of the statement t
 
 **Important**
 
-We slightly modified the Classification Head of the XLMRobertaModelForSequenceClassification model (removed the tanh activation and the intermediate linear layer) as that improved the model performance for this task considerably. To correctly load the full model you have to provide the ```trust_remote_code=True``` argument in the from_pretrained loading call.
-
+We slightly modified the Classification Head of the `XLMRobertaModelForSequenceClassification` model (removed the tanh activation and the intermediate linear layer) as that improved the model performance for this task considerably.
+To correctly load the full model, include the `trust_remote_code=True` argument when using the `from_pretrained method`.
 
 ## How to use