Update modeling_mimo.py

modeling_mimo.py

@@ -27,10 +27,10 @@ class MiMoMTPLayers(nn.Module):
                     hidden_states,
                     attention_mask,
                     position_ids,
-                    past_key_values: Optional[Cache]=None,
+                    past_key_value: Optional[Cache]=None,
                     output_attentions: Optional[bool]=False,
                     use_cache: Optional[bool]=False,
-                    position_embedding: Optional[Tuple[torch.Tensor, torch.Tensor]] = None,
+                    position_embeddings: Optional[Tuple[torch.Tensor, torch.Tensor]] = None,
                     cache_position=None,
                     **kwargs):
         input_embeds = self.token_layernorm(input_embeds)
@@ -38,15 +38,15 @@ class MiMoMTPLayers(nn.Module):
         hidden_states = self.input_proj(torch.cat([previous_hidden_states, input_embeds], dim=-1))
         residual = hidden_states
         hidden_states = self.input_layernorm(hidden_states)
-        hidden_states, _ = self.self_attn(hidden_states,
+        hidden_states = self.self_attn(hidden_states,
                                        attention_mask=attention_mask,
                                        position_ids=position_ids,
-                                       past_key_values=past_key_values,
+                                       past_key_value=past_key_value,
                                        output_attentions=output_attentions,
                                        use_cache=use_cache,
                                        cache_position=cache_position,
-                                       position_embedding=position_embedding,
-                                       **kwargs)
+                                       position_embeddings=position_embeddings,
+                                       **kwargs)[0]
         hidden_states = residual + hidden_states
         residual = hidden_states
         hidden_states = self.post_attention_layernorm(hidden_states)