update

README.md

@@ -200,12 +200,12 @@ print(outputs)
 <details>
 <summary>👉 Click to expand: Use flash-attn to boost performance and reduce memory usage</summary>
 
-<pre><code>
+```shell
 # ensure the flash-attn2 is installed
 pip install flash-attn --no-build-isolation
-</code></pre>
+```
 
-<pre><code>
+```python
 import torch
 from transformers import AutoModelForCausalLM, AutoProcessor
 from PIL import Image
@@ -260,7 +260,7 @@ with torch.inference_mode():
 
 outputs = processor.batch_decode(out, skip_special_tokens=True)[0]
 print(outputs)
-</code></pre>
+```
 
 </details>