Update app.py

app.py

@@ -21,7 +21,9 @@ def respond(
     temperature,
     top_p,
 ):
-    messages = [{"role": "system", "content": system_message}]
+    messages = []
+    if system_message:
+        messages = [{"role": "system", "content": system_message}]
     
     for user, assistant in history:
         if user:
@@ -33,7 +35,7 @@ def respond(
 
     try:
         stream = client.chat.completions.create(
-            model="Deepseek-R1-0528-Qwen3-8B",  # ⚠️ Replace it with the name of the model loaded by your llama.cpp
+            model="Deepseek-R1-0528-Qwen3-8B",
             messages=messages,
             max_tokens=max_tokens,
             temperature=temperature,
@@ -43,8 +45,7 @@ def respond(
 
         output = ""
         for chunk in stream:
-            print(chunk)
-            delta = chunk.choices[0].delta.content or ""
+            delta = chunk.choices[0].delta.content or chunk.choices[0].delta.reasoning_content or ""
             output += delta
             yield output
 
@@ -55,8 +56,8 @@ def respond(
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly assistant.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=4096, step=1, label="Max new tokens"),
+        gr.Textbox(value=".", label="System message"),
+        gr.Slider(minimum=1, maximum=8000, value=4096, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],