einops.EinopsError: Error while processing rearrange-reduction pattern "b pytorch_model.bin.index.json t h w -> (b pytorch_model.bin.index.json) pytorch_model.bin.index.json (t h w)".

[1145284121]

Allegro/allegro/models/transformers/transformer_3d_allegro.py", line 307, in forward
attention_mask_vid = rearrange(attention_mask_vid, 'b pytorch_model.bin.index.json t h w -> (b pytorch_model.bin.index.json) pytorch_model.bin.index.json (t h w)')
File "/root/miniconda3/envs/allegro/lib/python3.10/site-packages/einops/einops.py", line 591, in rearrange
return reduce(tensor, pattern, reduction="rearrange", **axes_lengths)
File "/root/miniconda3/envs/allegro/lib/python3.10/site-packages/einops/einops.py", line 533, in reduce
raise EinopsError(message + "\n {}".format(e))
einops.EinopsError: Error while processing rearrange-reduction pattern "b pytorch_model.bin.index.json t h w -> (b pytorch_model.bin.index.json) pytorch_model.bin.index.json (t h w)".
Input tensor shape: torch.Size([2, 1, 22, 45, 80]). Additional info: {}.

I tried transformer==4.40.1 and 4.37.1, all encountered this error