diff --git a/models.py b/models.py
index deb2338..73c5f3b 100644
--- a/models.py
+++ b/models.py
@@ -800,7 +800,7 @@ class WindowAttention(nn.Module):
 
         # cosine attention
         attn = (F.normalize(q, dim=-1) @ F.normalize(k, dim=-1).transpose(-2, -1))
-        logit_scale = torch.clamp(self.logit_scale, max=torch.log(torch.tensor(1. / 0.01))).exp()
+        logit_scale = torch.clamp(self.logit_scale, max=torch.log(torch.tensor(1. / 0.01)).cuda()).exp()
         attn = attn * logit_scale
 
         relative_position_bias_table = self.cpb_mlp(self.relative_coords_table).view(-1, self.num_heads)