Update app.py

app.py

@@ -1,6 +1,8 @@
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 import gradio as gr
+import spaces
+
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 # تحميل النموذج والمحول
@@ -13,6 +15,7 @@ model = AutoModelForCausalLM.from_pretrained(
     device_map="auto",
     trust_remote_code=True
 )
+@spaces.GPU
 
 # دالة الرد
 def respond(message, chat_history):
@@ -47,4 +50,4 @@ chat = gr.ChatInterface(
 )
 
 # تشغيل التطبيق
-chat.launch(share=True)
+chat.launch()