Update app.py

app.py

@@ -14,26 +14,26 @@ client = InferenceClient("Qwen/Qwen2.5-Coder-32B-Instruct")
 
 client = InferenceClient("Qwen/Qwen2.5-Coder-32B-Instruct")
 
-def greet(messages):
+def greet(message):
     response = ""
-    for message in client.chat_completion(
-        messages,
+    for token in client.text_generation(
+        message,
         stream=True,
-        max_tokens=1024,
+        max_new_tokens=12,
         temperature=0.7,
         top_p=0.95
     ):
-        token = message.choices[0].delta.content
+        print(token)
         response += token
         yield response
 
 demo = gr.Interface(
     fn=greet,
     inputs=[
-        gr.JSON(value=[{"role": "user", "content": "Bạn là AI"}])
+        gr.Textbox(label="message", value="The huggingface_hub library is ")
     ],
     outputs=[gr.Textbox(label="result", lines=3)],
-    api_name="chat",
+    api_name="generate",
     clear_btn=None
 )