Update modeling_Llamoe.py

modeling_Llamoe.py

@@ -561,10 +561,15 @@ class LlamoeSdpaAttention(LlamoeAttention):
 
         bsz, q_len, _ = hidden_states.size()
 
+        print("bsz:",bsz.shape)
+        print("q_len:",q_len.shape)
+        print("hidden_states:",hidden_states.shape)
         query_states = self.q_proj(hidden_states)
         key_states = self.k_proj(hidden_states)
         value_states = self.v_proj(hidden_states)
-
+        print("query_states:",query_states.shape)
+        print("key_states:",key_states.shape)
+        print("value_states:",value_states.shape)
         query_states = query_states.view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2)
         key_states = key_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2)
         value_states = value_states.view(bsz, q_len, self.num_key_value_heads, self.head_dim).transpose(1, 2)