Update README.md

README.md

@@ -17,4 +17,4 @@ This model is based on the norkart/mt5-large-no checkpoint and then trained for
 Given a question and a context, the model can find the answer in the context. The answer does not need to be stated verbatim in the context.
 
 Format:
-"question: <your question> context: <context to the question>"
+"question: 'your question' context: 'context to the question'"