fix-torch.torch should be torch

modeling_llada2_moe.py

@@ -81,7 +81,7 @@ def _get_unpad_data(attention_mask):
     indices = torch.nonzero(attention_mask.flatten(), as_tuple=False).flatten()
     max_seqlen_in_batch = seqlens_in_batch.max().item()
     cu_seqlens = F.pad(
-        torch.cumsum(seqlens_in_batch, dim=0, dtype=torch.torch.int32), (1, 0)
+        torch.cumsum(seqlens_in_batch, dim=0, dtype=torch.int32), (1, 0)
     )
     return (
         indices,