Update modeling_minicpm.py ——.flatten()

modeling_minicpm.py

@@ -78,7 +78,7 @@ def _get_unpad_data(attention_mask):
     seqlens_in_batch = attention_mask.sum(dim=-1, dtype=torch.int32)
     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))
+    cu_seqlens = F.pad(torch.cumsum(seqlens_in_batch.flatten(), dim=0, dtype=torch.torch.int32), (1, 0))
     return (
         indices,
         cu_seqlens,