Update README.md

README.md

@@ -117,7 +117,9 @@ outputs_all = llm.generate(prompts, sampling_params)
 evaluator_text = [output.outputs[0].text.split(tokenizer.eos_token)[0] for output in outputs_all]
 
 print(evaluator_text[0])
-# Explanation: Both Assistant A and Assistant B provided a numerical answer to the question, but Assistant A's answer is correct, while Assistant B's answer is incorrect. The question asks for the sum of 5 and 10, which is 15. Therefore, Assistant A's response is more accurate and reliable.\n\nVerdict: [A]"
+# Explanation: Both Assistant A and Assistant B provided a numerical answer to the question, but Assistant A's answer is correct, while Assistant B's answer is incorrect. The question asks for the sum of 5 and 10, which is 15. Therefore, Assistant A's response is more accurate and reliable.
+# 
+# Verdict: [A]
 ```