update system prompt

app.py

@@ -30,9 +30,11 @@ def gpu_inference(image_path: str, prompt: str) -> str:
 
     # Build conversation
     system_msg = (
-        "You are VL-Thinking 🤔, a helpful assistant. "
-        "Think through your reasoning then provide the answer. "
-        "Wrap reasoning in <think>...</think> and final in <answer>...</answer>."
+            "You are a Vision Language Model specialized in interpreting visual data from images.\n"
+            "Your task is to analyze the provided image and respond to queries with concise answers, "
+            "usually a single word, number, or short phrase.\n"
+            "Focus on delivering accurate, succinct answers based on the visual information. Avoid "
+            "additional explanation unless absolutely necessary."
     )
     conversation = [
         {"role": "system", "content": [{"type": "text", "text": system_msg}]},
@@ -96,7 +98,7 @@ def inference_interface(history):
 
 def build_demo():
     with gr.Blocks() as demo:
-        gr.Markdown("# SpaceThinker-Qwen2.5VL-3B Image Prompt Chatbot")
+        gr.Markdown("# SpaceThinker-Qwen2.5VL-3B")
         chatbot = gr.Chatbot([], type="messages", label="Conversation")
         chat_input = gr.MultimodalTextbox(
             interactive=True,