Update README.md

README.md

@@ -84,7 +84,7 @@ generated_ids = [
 response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 ```
 
-Here is an example of the question "Is 9.9 or 9.10 larger", sampled greedily. It gets the question correct, but the reasoning seems a bit weird. At the beginning its pretty strong but when it tries to solve the problem from another view it's starting to deviate. 
+Here is an example of the question "Is 9.9 or 9.10 larger", sampled greedily. It gets the question correct, but the reasoning seems a bit weird. At the beginning its pretty strong but when it tries to solve the problem from another view it's starting to deviate. Then at the end it gets back on track and outputs the correct answer:
 ```
 <|im_start|>system
 You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.<|im_end|>