updated

modeling_hymba.py

@@ -1601,16 +1601,16 @@ class HymbaBlock(nn.Module):
         if self.reuse_kv:
             query_states, hidden_states = hidden_states.tensor_split((self.attn_hidden_size,), dim=1)
             query_states = query_states.transpose(1,2)
-            print("[DEBUG] query_states shape: ", query_states.shape)
+            print("[DEBUG] query_states shape: ", query_states)
         else:
             query_states, key_states, value_states, hidden_states = hidden_states.tensor_split((self.attn_hidden_size, self.attn_hidden_size + self.k_hidden_size, self.attn_hidden_size + self.k_hidden_size + self.v_hidden_size), dim=1)
 
             query_states = query_states.transpose(1,2)
             key_states = key_states.transpose(1,2)
             value_states = value_states.transpose(1,2)
-            print("[DEBUG] query_states shape: ", query_states.shape)
-            print("[DEBUG] key_states shape: ", key_states.shape)
-            print("[DEBUG] value_states shape: ", value_states.shape)
+            print("[DEBUG] query_states shape: ", query_states)
+            print("[DEBUG] key_states shape: ", key_states)
+            print("[DEBUG] value_states shape: ", value_states)
 
         if use_precomputed_states:
             hidden_states = causal_conv1d_update(