fix for transformers-4.33.1

modeling_decicoder.py

@@ -36,6 +36,7 @@ class DeciCoderAttention(LlamaAttention):
         self.num_key_value_groups = self.num_heads // self.num_key_value_heads
         self.pretraining_tp = config.pretraining_tp
         self.max_position_embeddings = config.max_position_embeddings
+        self.rope_theta = getattr(config, 'rope_theta', None)
 
         if (self.head_dim * self.num_heads) != self.hidden_size:
             raise ValueError(