Update app.py

app.py

@@ -14,7 +14,7 @@ model = AutoModelForCausalLM.from_pretrained(
     "stabilityai/stable-code-3b",
     trust_remote_code=True,
     torch_dtype="auto",
-    attn_implementation="flash_attention_2",
+#   attn_implementation="flash_attention_2",
 ).to("cuda" if torch.cuda.is_available() else "cpu")
 
 @spaces.GPU