diff --git a/model/model_minimind.py b/model/model_minimind.py
index 4b43610..b76b993 100644
--- a/model/model_minimind.py
+++ b/model/model_minimind.py
@@ -141,6 +141,7 @@ class Attention(nn.Module):
         self.resid_dropout = nn.Dropout(args.dropout)
         self.dropout = args.dropout
         self.flash = hasattr(torch.nn.functional, 'scaled_dot_product_attention') and args.flash_attn
+        self.flash = hasattr(torch.nn.functional, 'scaled_dot_product_attention') and args.flash_attn and torch.cuda.is_available()
         # print("WARNING: using slow attention. Flash Attention requires PyTorch >= 2.0")
 
     def forward(self,