FIX Change check if past_key_values is empty

After transformers merged this PR:

huggingface/transformers#33703

The bool of past_key_values (a Cache instance) would change from False
to True in one of our checks. Use get_seq_length() method instead, which
is consistent before and after that commit.

I checked the tests with the new change for both transformers before and
after that commit and they passed, so this change should be backwards
compatible.

src/peft/peft_model.py

@@ -1776,7 +1776,7 @@ def prepare_inputs_for_generation(self, *args, task_ids: Optional[torch.Tensor]
 
  # no past_key_values or past_key_values empty cache
  requires_prompt_injection = (model_kwargs["past_key_values"] is None) or (
- isinstance(model_kwargs["past_key_values"], transformers.Cache) and not model_kwargs["past_key_values"]
+ isinstance(model_kwargs["past_key_values"], transformers.Cache) and not model_kwargs["past_key_values"].get_seq_length()
  )
 
  if requires_prompt_injection and peft_config.peft_type == PeftType.PREFIX_TUNING: