Update README.md

README.md

@@ -254,9 +254,7 @@ You can find more examples at [our project page](https://yonsei-mir.github.io/Ak
 
 ## Warning
 
-- Model may experience hallucinations and repetition of the same words depending on the decoding strategy.
-- The results generated by AKALlma may include inaccurate or harmful outcomes.
-- As the model is trained with a fixed system prompt, a different system prompt may decrease the performance.
+Although AKALlama-70B has significant potential, its responses can sometimes be inaccurate, biased, or misaligned, presenting risks if used without additional testing and refinement. Furthermore, the quality of the model's output is greatly influenced by the system prompt and decoding strategy. Changes in these areas could result in less precise outputs. Therefore, we strongly recommend handling our model with considerable caution.
 
 ## Comments