Method generate

bert/generation_utils.py:101–483

r""" Generates sequences for models with a LM head. The method currently supports greedy decoding, beam-search decoding, sampling with temperature, sampling with top-k or nucleus sampling. Adapted in part from `Facebook's XLM beam search code`_. .. _`Facebook's XLM beam search code

(
        self,
        input_ids: Optional[torch.LongTensor] = None,
        max_length: Optional[int] = None,
        min_length: Optional[int] = None,
        do_sample: Optional[bool] = None,
        early_stopping: Optional[bool] = None,
        num_beams: Optional[int] = None,
        temperature: Optional[float] = None,
        top_k: Optional[int] = None,
        top_p: Optional[float] = None,
        repetition_penalty: Optional[float] = None,
        bad_words_ids: Optional[Iterable[int]] = None,
        bos_token_id: Optional[int] = None,
        pad_token_id: Optional[int] = None,
        eos_token_id: Optional[int] = None,
        length_penalty: Optional[float] = None,
        no_repeat_ngram_size: Optional[int] = None,
        num_return_sequences: Optional[int] = None,
        attention_mask: Optional[torch.LongTensor] = None,
        decoder_start_token_id: Optional[int] = None,
        use_cache: Optional[bool] = None,
        **model_specific_kwargs
    )

    @torch.no_grad()
    def generate(
        self,
        input_ids: Optional[torch.LongTensor] = None,
        max_length: Optional[int] = None,
        min_length: Optional[int] = None,
        do_sample: Optional[bool] = None,
        early_stopping: Optional[bool] = None,
        num_beams: Optional[int] = None,
        temperature: Optional[float] = None,
        top_k: Optional[int] = None,
        top_p: Optional[float] = None,
        repetition_penalty: Optional[float] = None,
        bad_words_ids: Optional[Iterable[int]] = None,
        bos_token_id: Optional[int] = None,
        pad_token_id: Optional[int] = None,
        eos_token_id: Optional[int] = None,
        length_penalty: Optional[float] = None,
        no_repeat_ngram_size: Optional[int] = None,
        num_return_sequences: Optional[int] = None,
        attention_mask: Optional[torch.LongTensor] = None,
        decoder_start_token_id: Optional[int] = None,
        use_cache: Optional[bool] = None,
        **model_specific_kwargs
    ) -> torch.LongTensor:
        r""" Generates sequences for models with a LM head. The method currently supports greedy decoding, beam-search decoding, sampling with temperature, sampling with top-k or nucleus sampling.

        Adapted in part from `Facebook's XLM beam search code`_.

        .. _`Facebook's XLM beam search code`:
           https://github.com/facebookresearch/XLM/blob/9e6f6814d17be4fe5b15f2e6c43eb2b2d76daeb4/src/model/transformer.py#L529


        Parameters:

            input_ids: (`optional`) `torch.LongTensor` of shape `(batch_size, sequence_length)`
                The sequence used as a prompt for the generation. If `None` the method initializes
                it as an empty `torch.LongTensor` of shape `(1,)`.

            max_length: (`optional`) int
                The max length of the sequence to be generated.  Between `min_length` and infinity. Default to 20.

            min_length: (`optional`) int
                The min length of the sequence to be generated.  Between 0 and infinity. Default to 0.

            do_sample: (`optional`) bool
                If set to `False` greedy decoding is used. Otherwise sampling is used. Defaults to `False` as defined in `configuration_utils.PretrainedConfig`.

            early_stopping: (`optional`) bool
                if set to `True` beam search is stopped when at least `num_beams` sentences finished per batch. Defaults to `False` as defined in `configuration_utils.PretrainedConfig`.

            num_beams: (`optional`) int
                Number of beams for beam search. Must be between 1 and infinity. 1 means no beam search. Default to 1.

            temperature: (`optional`) float
                The value used to module the next token probabilities. Must be strictly positive. Default to 1.0.

            top_k: (`optional`) int
                The number of highest probability vocabulary tokens to keep for top-k-filtering. Between 1 and infinity. Default to 50.