Update app.py

app.py

@@ -101,8 +101,8 @@ with gr.Blocks(theme=gr.themes.Default(primary_hue="blue", secondary_hue="neutra
         """
 
         #Disable Qwen3 thinking
-        #if "Qwen3".lower() in current_selected_model:
-        #    system_prompt = system_prompt+" /no_think"
+        if "Qwen3".lower() in current_selected_model:
+            system_prompt = system_prompt+" /no_think"
         
         # The 'history' variable from Gradio contains the entire conversation.
         # We prepend the system prompt to this history to form the final payload.
@@ -116,8 +116,7 @@ with gr.Blocks(theme=gr.themes.Default(primary_hue="blue", secondary_hue="neutra
         response_stream = ollama.chat(
             model=current_selected_model, # Use the dynamically selected model
             messages=messages,
-            stream=True,
-            think=False
+            stream=True
         )
 
         # Iterate through the stream, updating the placeholder with each new chunk.