Update app.py

app.py

@@ -1,6 +1,8 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import spaces
 
+@spaces.GPU  # مهم لـ ZeroGPU!
 def respond(
     message,
     history: list[dict[str, str]],
@@ -8,44 +10,36 @@ def respond(
     max_tokens,
     temperature,
     top_p,
-    hf_token: gr.OAuthToken,
 ):
-    client = InferenceClient(token=hf_token.token, model="anaspro/iraqi-kashif-2b")
+    client = InferenceClient(model="anaspro/iraqi-kashif-2b")
     
     messages = [{"role": "system", "content": system_message}]
     messages.extend(history)
     messages.append({"role": "user", "content": message})
     
     response = ""
-    for message in client.chat_completion(
+    for msg in client.chat_completion(
         messages,
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
-        response += token
-        yield response
+        if msg.choices and msg.choices[0].delta.content:
+            token = msg.choices[0].delta.content
+            response += token
+            yield response
 
 chatbot = gr.ChatInterface(
     respond,
     type="messages",
     additional_inputs=[
         gr.Textbox(value="أنت مساعد عراقي ذكي.", 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=512, value=100, step=1, label="Max tokens"),
+        gr.Slider(minimum=0.1, maximum=2.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p"),
     ],
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
 if __name__ == "__main__":
-    demo.launch()
+    chatbot.launch()