Update app.py

app.py

@@ -1,16 +1,25 @@
 import gradio as gr
+import spaces
+import torch
 from transformers import pipeline
 
 MODEL_ID = "Qwen/Qwen2.5-7B-Instruct"
 
-pipe = pipeline(
-    "text-generation",
-    model=MODEL_ID,
-    device_map="auto"
-)
+pipe = None
 
+def load_model():
+    global pipe
+    if pipe is None:
+        pipe = pipeline(
+            "text-generation",
+            model=MODEL_ID,
+            device_map="auto"
+        )
+
+@spaces.GPU
 def chat_fn(message, history):
-    history = history or []
+    load_model()
+
     outputs = pipe(
         message,
         max_new_tokens=256,