Update modeling_tanuki.py

modeling_tanuki.py

@@ -857,6 +857,8 @@ class TanukiSparseMoeBlock(nn.Module):
         for expert_idx in range(self.num_experts):
             expert_layer = self.experts[expert_idx]
             idx, top_x = torch.where(expert_mask[expert_idx])
+            if top_x.shape[0] == 0:
+                continue
 
             # Index the correct hidden states and compute the expert hidden state for
             # the current expert. We need to make sure to multiply the output hidden