Updated model to be better

app.py

@@ -5,8 +5,7 @@ from transformers import pipeline
 pipe = pipeline(
     "text-generation",
     model="microsoft/Phi-3-mini-4k-instruct",
-    torch_dtype="auto",
-    device_map=1,
+    device=-1,          # <-- forces CPU
     max_new_tokens=300
 )