Update README.md

README.md

@@ -9,4 +9,19 @@ widget:
 ---
 This is the model used for knowledge clustering where we feed title-body pair and the classifier predicts if the pair is valid or not.
 For further information, please refer to https://github.com/yctam/dstc10_track2_task2 for the Github repository.
----
+
+## Usage
+def single_test(tokenizer, title_body_pair):
+    result = tokenizer([title_body_pair], return_tensors="pt")
+    result.to(device)
+    model.eval()
+    outputs = model(**result)
+    predictions = outputs.logits.argmax(dim=-1)
+    return True if predictions == 0 else False
+
+if __name__ == '__main__':
+    sentence = "Can I check in anytime?"
+    body = "Yes, 24 Hours Front Desk Avaliable."
+    pair = (sentence, body)
+    print(single_test(pair)) # Expect: True       
+---