Update optimum/habana/transformers/models/mt5/modeling_mt5.py

Co-authored-by: Yaser Afshar <yaser.afshar@intel.com>

optimum/habana/transformers/models/mt5/modeling_mt5.py

@@ -477,7 +477,7 @@ def gaudi_MT5Stack_forward(
 
             # layer_outputs is a tuple with:
             # hidden-states, key-value-states, (self-attention position bias), (self-attention weights), (cross-attention position bias), (cross-attention weights)
-            if use_cache is False:
+            if not use_cache:
                 layer_outputs = layer_outputs[:1] + (None,) + layer_outputs[1:]
 
             hidden_states, present_key_value_state = layer_outputs[:2]