Update README.md

README.md

@@ -19,6 +19,8 @@ PROMPT FORMAT: [chatml](https://github.com/openai/openai-python/blob/main/chatml
 
 CURRENT MMLU: stem ACC: 43.12 Humanities ACC: 45.15 other ACC: 56.40 social ACC: 57.96 AVERAGE ACC:49.61
 
+Issue: Compared to the original Qwen, the MMLU score dropped slightly (4.59) due to insufficient realignment, but the proportions of each item changed, which is unusual.
+
 [在制品]
 
 这是 [通义千问 Qwen/Qwen-7B-Chat](https://huggingface.co/Qwen/Qwen-7B-Chat) 的 LLaMA 化版本，经过重新校准以适应原始的类似 LLaMA/LLaMA-2 的模型结构。
@@ -29,4 +31,6 @@ CURRENT MMLU: stem ACC: 43.12 Humanities ACC: 45.15 other ACC: 56.40 social ACC:
 
 PROMPT 格式: [chatml](https://github.com/openai/openai-python/blob/main/chatml.md)
 
-当前的 MMLU: stem ACC: 43.12 Humanities ACC: 45.15 other ACC: 56.40 social ACC: 57.96 AVERAGE ACC:49.61
+当前的 MMLU: stem ACC: 43.12 Humanities ACC: 45.15 other ACC: 56.40 social ACC: 57.96 AVERAGE ACC:49.61
+
+问题：相比原本的Qwen，由于不够充分的重新对齐，MMLU分数略有下降（4.59），但是各项目的比例发生了变化，这是不寻常的。