extra line

2023-08-04 16:52:04 +07:00
parent f2e34e6b0a
commit 11a8348dfc
1 changed files with 0 additions and 1 deletions
@@ -108,7 +108,6 @@ class Attention(nn.Module):

        # use flash attention or a manual implementation?
        self.flash = hasattr(torch.nn.functional, 'scaled_dot_product_attention')
-
        if not self.flash:
            print("WARNING: using slow attention. Flash Attention requires PyTorch >= 2.0")
            mask = torch.full((1, 1, args.max_seq_len, args.max_seq_len), float("-inf"))