Update modeling_Llamoe.py

modeling_Llamoe.py

@@ -525,7 +525,7 @@ class LlamoeFlashAttention2(LlamoeAttention):
 
 
 # Copied from transformers.models.llama.modeling_llama.LlamaSdpaAttention with Llama->Gemmoe
-class LlamoeSdpaAttention(GemmoeAttention):
+class LlamoeSdpaAttention(LlamoeAttention):
     """
     Gemmoe attention module using torch.nn.functional.scaled_dot_product_attention. This module inherits from
     `GemmoeAttention` as the weights of the module stays untouched. The only changes are on the forward pass to adapt to