fixed structure

app.py

@@ -12,8 +12,6 @@ DEFAULT_MAX_NEW_TOKENS = 4000
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 DESCRIPTION = """\
-# Llama-3.1 8B Stanford Encyclopedia of Philosophy Chat
-
 This Space showcases the Llama3.1-Instruct-SEP-Chat model from ruggsea, a fine-tuned instruction version of Meta's Llama 3.1 8B model, specifically tailored for philosophical discussions with a formal and informative tone. The model was trained using the Stanford Encyclopedia of Philosophy dataset and carefully crafted prompts.
 
 Feel free to engage in philosophical discussions and ask questions. The model supports multi-turn conversations and will maintain context.
@@ -99,69 +97,6 @@ def generate(
         gr.Warning(f"Error during generation: {str(e)}")
         yield "I apologize, but I encountered an error. Please try again."
 
-chat_interface = gr.ChatInterface(
-    fn=generate,
-    additional_inputs=[
-        gr.Textbox(
-            label="System prompt", 
-            lines=6,
-            value="You are a knowledgeable philosophy professor using the Stanford Encyclopedia of Philosophy as your knowledge base. Provide clear, accurate responses using markdown formatting. Focus on philosophical concepts and maintain academic rigor while being accessible. Always cite relevant philosophers and concepts."
-        ),
-        gr.Slider(
-            label="Max new tokens",
-            minimum=1,
-            maximum=MAX_MAX_NEW_TOKENS,
-            step=1,
-            value=DEFAULT_MAX_NEW_TOKENS,
-        ),
-        gr.Slider(
-            label="Temperature",
-            minimum=0.1,
-            maximum=4.0,
-            step=0.1,
-            value=0.7,
-        ),
-        gr.Slider(
-            label="Top-p (nucleus sampling)",
-            minimum=0.05,
-            maximum=1.0,
-            step=0.05,
-            value=0.9,
-        ),
-        gr.Slider(
-            label="Top-k",
-            minimum=1,
-            maximum=1000,
-            step=1,
-            value=50,
-        ),
-        gr.Slider(
-            label="Repetition penalty",
-            minimum=1.0,
-            maximum=2.0,
-            step=0.05,
-            value=1.1,
-        ),
-    ],
-    stop_btn=None,
-    examples=[
-        ["What is the trolley problem and what are its main ethical implications?"],
-        ["Can you explain Plato's Theory of Forms?"],
-        ["What is the difference between analytic and continental philosophy?"],
-        ["How does Kant's Categorical Imperative work?"],
-        ["What is the problem of consciousness in philosophy of mind?"],
-    ],
-    title="Philosophy Chat with Llama 3.1",
-    chatbot=gr.Chatbot(
-        show_label=False,
-        avatar_images=(None, None),
-    ),
-    autofocus=True,
-    retry_btn=None,
-    undo_btn=None,
-    clear_btn=None,
-)
-
 with gr.Blocks(css="style.css") as demo:
     gr.Markdown("# Philosophy Chat with Llama 3.1")
     gr.Markdown(DESCRIPTION)
@@ -169,7 +104,72 @@ with gr.Blocks(css="style.css") as demo:
         value="Duplicate Space for private use",
         elem_id="duplicate-button"
     )
-    chat_interface.render()
+    
+    # Add some spacing
+    gr.Markdown("<br>")
+    
+    chat_interface = gr.ChatInterface(
+        fn=generate,
+        additional_inputs=[
+            gr.Textbox(
+                label="System prompt", 
+                lines=6,
+                value="You are a knowledgeable philosophy professor using the Stanford Encyclopedia of Philosophy as your knowledge base. Provide clear, accurate responses using markdown formatting. Focus on philosophical concepts and maintain academic rigor while being accessible. Always cite relevant philosophers and concepts."
+            ),
+            gr.Slider(
+                label="Max new tokens",
+                minimum=1,
+                maximum=MAX_MAX_NEW_TOKENS,
+                step=1,
+                value=DEFAULT_MAX_NEW_TOKENS,
+            ),
+            gr.Slider(
+                label="Temperature",
+                minimum=0.1,
+                maximum=4.0,
+                step=0.1,
+                value=0.7,
+            ),
+            gr.Slider(
+                label="Top-p (nucleus sampling)",
+                minimum=0.05,
+                maximum=1.0,
+                step=0.05,
+                value=0.9,
+            ),
+            gr.Slider(
+                label="Top-k",
+                minimum=1,
+                maximum=1000,
+                step=1,
+                value=50,
+            ),
+            gr.Slider(
+                label="Repetition penalty",
+                minimum=1.0,
+                maximum=2.0,
+                step=0.05,
+                value=1.1,
+            ),
+        ],
+        stop_btn=None,
+        examples=[
+            ["What is the trolley problem and what are its main ethical implications?"],
+            ["Can you explain Plato's Theory of Forms?"],
+            ["What is the difference between analytic and continental philosophy?"],
+            ["How does Kant's Categorical Imperative work?"],
+            ["What is the problem of consciousness in philosophy of mind?"],
+        ],
+        chatbot=gr.Chatbot(
+            show_label=False,
+            avatar_images=(None, None),
+        ),
+        autofocus=True,
+        retry_btn=None,
+        undo_btn=None,
+        clear_btn=None,
+    )
+    
     gr.Markdown(LICENSE)
 
 if __name__ == "__main__":