t`, *optional*, defaults to 1):
            The id of the token to force as the last generated token when `max_length` is reached. Usually set to
            `eos_token_id`.
        num_global_tokens (`int`, *optional*, defaults to 128):
            Number of global tokens to use for the encoder
        block_size (`int`, *optional*, defaults to 512):
            Block size for encoder local attention. Sequence length should be an exact multiple of block size.
            block_size must be a multiple of 2 if stagger_local_block is True
        stagger_local_block (`bool`, *optional*, defaults to `True`):
            Whether to stagger every other local attention by half a block

    Example:

    ```python
    >>> from transformers import PegasusXConfig, PegasusXModel

    >>> # Initializing a PEGASUS google/pegasus-x-large style configuration
    >>> configuration = PegasusXConfig()

    >>> # Initializing a model (with random weights) from the google/pegasus-x-large style configuration
    >>> model = PegasusXModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```Z	pegasus_xZpast_key_valuesÚ