Update README.md

README.md

@@ -78,11 +78,12 @@ Breeze-7B-32k-Base clears the tasks with 90+% accuracy, shown in the figure belo
 
 ## Use in Transformers
 
-First install direct dependencies:
+First, install direct dependencies:
 ```
 pip install transformers torch accelerate
 ```
-If you want faster inference using flash-attention2, you need to install these dependencies:
+<p style="color:red;">Flash-attention2 is strongly recommended for long context scenarios.</p>
+
 ```bash
 pip install packaging ninja
 pip install flash-attn