Update app.py

app.py

@@ -83,32 +83,14 @@ additional_inputs=[
 
 css = """
   #mkd {
-    height: 300px; 
+    height: 200px; 
     overflow: auto; 
     border: 1px solid #ccc; 
   }
 """
 
 with gr.Blocks(css=css) as demo:
-    gr.HTML("""<h2>🤖 Mistral Chat - Gradio 🤖</h2>
-        In this demo, you can chat with <a href='https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1'>Mistral-7B-Instruct</a> model. 💬
-        Learn more about the model <a href='https://huggingface.co/docs/transformers/main/model_doc/mistral'>here</a>. 📚
-        <h2>🛠 Model Features 🛠</h2>
-        <ul>
-          <li>🪟 Sliding Window Attention with 128K tokens span</li>
-          <li>🚀 GQA for faster inference</li>
-          <li>📝 Byte-fallback BPE tokenizer</li>
-        </ul>
-        <h3>📜 License 📜  Released under Apache 2.0 License</h3>
-        <h3>📦 Usage 📦</h3>
-        <ul>
-          <li>📚 Available on Huggingface Hub</li>
-          <li>🐍 Python code snippets for easy setup</li>
-          <li>📈 Expected speedups with Flash Attention 2</li>
-        </ul>
-    """)
-
-    
+  
     gr.ChatInterface(
         generate,
         additional_inputs=additional_inputs,
@@ -128,5 +110,21 @@ with gr.Blocks(css=css) as demo:
         ["Create a ten-point markdown outline with emojis about: Pneumocystitis jiroveci"]
         ]
     )
-
+    gr.HTML("""<h2>🤖 Mistral Chat - Gradio 🤖</h2>
+        In this demo, you can chat with <a href='https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1'>Mistral-7B-Instruct</a> model. 💬
+        Learn more about the model <a href='https://huggingface.co/docs/transformers/main/model_doc/mistral'>here</a>. 📚
+        <h2>🛠 Model Features 🛠</h2>
+        <ul>
+          <li>🪟 Sliding Window Attention with 128K tokens span</li>
+          <li>🚀 GQA for faster inference</li>
+          <li>📝 Byte-fallback BPE tokenizer</li>
+        </ul>
+        <h3>📜 License 📜  Released under Apache 2.0 License</h3>
+        <h3>📦 Usage 📦</h3>
+        <ul>
+          <li>📚 Available on Huggingface Hub</li>
+          <li>🐍 Python code snippets for easy setup</li>
+          <li>📈 Expected speedups with Flash Attention 2</li>
+        </ul>
+    """)
 demo.queue().launch(debug=True)