Class SynthIDTextWatermarkingConfig

configuration_utils.py:1501–1587

Class that holds arguments for watermark generation and should be passed into `GenerationConfig` during `generate`. See [this paper](https://www.nature.com/articles/s41586-024-08025-4) for more details on the arguments. Args: ngram_len (`int`): Ngram length.

@dataclass
class SynthIDTextWatermarkingConfig(BaseWatermarkingConfig):
    """
    Class that holds arguments for watermark generation and should be passed into `GenerationConfig` during `generate`.
    See [this paper](https://www.nature.com/articles/s41586-024-08025-4) for more details on the arguments.

    Args:
        ngram_len (`int`):
            Ngram length.
        keys (`List[int]`):
            A sequence of watermarking keys, one for each depth.
        context_history_size (`int`, *optional*, defaults to 1024):
            Size of the tensor to keep track of seen contexts.
        sampling_table_seed (`int`, *optional*, defaults to 0):
            Random seed to generate the sampling table.
        sampling_table_size (`int`, *optional*, defaults to 65536):
            Size of the sampling table.
        skip_first_ngram_calls (`bool`, *optional*, defaults to `False`):
            Whether to skip first ngram calls.
        debug_mode (`bool`, optional, *optional*, defaults to `False`):
            Logits are modified to uniform one got before watermarking modification is applied. This is to test the
            implementation.

    Examples:
    ```python
    >>> from transformers import AutoModelForCausalLM, AutoTokenizer, SynthIDTextWatermarkingConfig

    >>> tokenizer = AutoTokenizer.from_pretrained('google/gemma-2-2b', padding_side="left")
    >>> model = AutoModelForCausalLM.from_pretrained('google/gemma-2-2b')

    >>> # SynthID Text configuration
    >>> watermarking_config = SynthIDTextWatermarkingConfig(
    ...     keys=[654, 400, 836, 123, 340, 443, 597, 160, 57],
    ...     ngram_len=5,
    ... )

    >>> # Generation with watermarking
    >>> tokenized_prompts = tokenizer(["Once upon a time, "], return_tensors="pt", padding=True)
    >>> output_sequences = model.generate(
    ...     **tokenized_prompts, watermarking_config=watermarking_config, do_sample=True, max_new_tokens=10
    ... )
    >>> watermarked_text = tokenizer.batch_decode(output_sequences, skip_special_tokens=True)
    ```
    """

    def __init__(
        self,
        ngram_len: int,
        keys: List[int],
        context_history_size: int = 1024,
        sampling_table_seed: int = 0,
        sampling_table_size: int = 2**16,
        skip_first_ngram_calls: bool = False,
        debug_mode: bool = False,
    ):
        self.ngram_len = ngram_len
        self.keys = keys
        self.sampling_table_size = sampling_table_size
        self.sampling_table_seed = sampling_table_seed