Update modeling_Llamoe.py

modeling_Llamoe.py

@@ -320,7 +320,7 @@ def repeat_kv(hidden_states: torch.Tensor, n_rep: int) -> torch.Tensor:
 class LlamoeAttention(nn.Module):
     """Multi-headed attention from 'Attention Is All You Need' paper"""
 
-    def __init__(self, config: LlamaConfig, layer_idx: Optional[int] = None):
+    def __init__(self, config: LlamoeConfig, layer_idx: Optional[int] = None):
         super().__init__()
         self.config = config
         self.layer_idx = layer_idx