Update app.py

app.py

@@ -12,18 +12,16 @@ def respond(
     hf_token: gr.OAuthToken,
 ):
     """
-    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+    Để biết thêm thông tin về hỗ trợ API Suy luận của `huggingface_hub`, vui lòng kiểm tra tài liệu: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
     """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
+    # Đã thay đổi mô hình thành Qwen/Qwen3-4B-Thinking-2507
+    client = InferenceClient(token=hf_token.token, model="Qwen/Qwen3-4B-Thinking-2507")
 
     messages = [{"role": "system", "content": system_message}]
-
     messages.extend(history)
-
     messages.append({"role": "user", "content": message})
 
     response = ""
-
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -35,21 +33,20 @@ def respond(
         token = ""
         if len(choices) and choices[0].delta.content:
             token = choices[0].delta.content
-
         response += token
         yield response
 
 
 """
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+Để biết thông tin về cách tùy chỉnh ChatInterface, hãy xem tài liệu của gradio: https://www.gradio.app/docs/chatinterface
 """
 chatbot = gr.ChatInterface(
     respond,
     type="messages",
     additional_inputs=[
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, 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=1, maximum=4096, value=512, step=1, label="Max new tokens"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(
             minimum=0.1,
             maximum=1.0,
@@ -67,4 +64,4 @@ with gr.Blocks() as demo:
 
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()