Update AsteriskForCausalLM.py

AsteriskForCausalLM.py

@@ -188,12 +188,14 @@ class HybridASPPAttentionLayer(LlamaDecoderLayer):
 
         # Attention branch - use parent's self_attn
         attn_outputs = self.self_attn(
-            hidden_states,
-            position_embeddings,
+            hidden_states=hidden_states,
             attention_mask=attention_mask,
+            position_ids=position_ids,
             past_key_values=past_key_values,
             cache_position=cache_position,
+            position_embeddings=position_embeddings,
         )
+
         attn_output = attn_outputs[0]
 
         # Gated fusion