Attention mask size problem

[XeonSid]

modeling_deepseek.py", line 829, in forward
raise ValueError(
ValueError: Attention mask should be of size (1, 1, 1, 30), but is torch.Size([1, 1, 1, 29])

I used the version with the requiredment.txt in my local letop and colab, still faced the same problem. i just can't get it.