Update README.md

README.md

@@ -76,6 +76,9 @@ print(f"the predction of the dataset : {final_output}")
 The Correct answer:-Option 1 
 ```
 
+##Preprocessing
+The text are tokenized using the GPT2 tokenizer.To feed the inputs of multiple choice we concatenated context and question with all the 4 possible choices.We used the first sentence as context+question and the second sentence as choices to feed 2 inputs to our tokenizer.
+
 ## Evaluation
 
 The following tables summarize the scores obtained by the **GPT2-CosmosQA**.