Update modeling_deepseekv2.py

modeling_deepseekv2.py

@@ -1786,7 +1786,7 @@ class DeepseekV2ForCausalLM(DeepseekV2PreTrainedModel):
         if past_key_values is not None:
             if isinstance(past_key_values, Cache):
                 cache_length = past_key_values.get_seq_length()
-                past_length = past_key_values.seen_tokens
+                past_length = getattr(past_key_values, "seen_tokens", cache_length)
                 max_cache_length = past_key_values.get_max_length()
             else:
                 cache_length = past_length = past_key_values[0][0].shape[2]