update cutoff correct qwen

app.py

@@ -55,4 +55,40 @@ def generate_response(message, history):
     
     # Correct format for conversational task
     messages = [{"role": "system", "content": system_instruction}]
-    for
+    for user_msg, assistant_msg in history:
+        messages.append({"role": "user", "content": user_msg})
+        messages.append({"role": "assistant", "content": assistant_msg})
+    messages.append({"role": "user", "content": message})
+
+    try:
+        # Switching to chat_completion for model compatibility
+        response = client.chat_completion(
+            messages,
+            max_tokens=1024,
+            stream=False
+        )
+        return response.choices[0].message.content
+    except Exception as error:
+        return f"System Error: {str(error)}. Verify your token permissions."
+
+custom_css = """
+body, .gradio-container { background-color: #0b0f19 !important; }
+footer {display: none !important}
+.message.user { background-color: #1e293b !important; border: 1px solid #3b82f6 !important; }
+.message.bot { background-color: #0f172a !important; color: #60a5fa !important; }
+"""
+
+with gr.Blocks(theme=gr.themes.Soft(primary_hue="blue"), css=custom_css) as demo:
+    gr.Markdown("# Advanced Logic Interface")
+    gr.ChatInterface(
+        fn=generate_response,
+        description="Inference layer utilizing state-hold logic.",
+        examples=[
+            "Run grid diagnostic",
+            "Calculate the integer distribution for 120 units across 3 nodes.",
+            "Explain network latency using technical terminology."
+        ]
+    )
+
+if __name__ == "__main__":
+    demo.launch()