Update app.py

app.py

@@ -53,11 +53,11 @@ def infer(prompt, max_tokens, temperature, top_k, top_p):
     return result[0]["generated_text"] if result and "generated_text" in result[0] else ""
 
 with gr.Blocks() as demo:
-    gr.Markdown("# GPT-OSS-20B 文字接龍推論")
+    gr.Markdown("# GPT-OSS-20B 文字接龍推論\n\n- 請參考[https://cookbook.openai.com/articles/openai-harmony](https://cookbook.openai.com/articles/openai-harmony)")
     with gr.Row():
         prompt = gr.Textbox(label="請輸入完整 prompt", value=default_text, lines=20, max_lines=40, show_copy_button=True)
     with gr.Row():
-        max_tokens = gr.Slider(1, 2048, value=512, step=1, label="最大生成 token 數 (max_tokens)")
+        max_tokens = gr.Slider(1, 2048, value=128, step=1, label="最大生成 token 數 (max_tokens)")
         temperature = gr.Slider(0.1, 2.0, value=1.0, step=0.01, label="溫度 (temperature)")
         top_k = gr.Slider(1, 100, value=40, step=1, label="Top-k")
         top_p = gr.Slider(0.0, 1.0, value=1.0, step=0.01, label="Top-p")