Method encode

gpu/tokenizer.py:95–156

Encodes a string into a list of token IDs. Args: s (str): The input string to be encoded. bos (bool): Whether to prepend the beginning-of-sequence token. eos (bool): Whether to append the end-of-sequence token. allowed_tokens (

(
        self,
        s: str,
        *,
        bos: bool,
        eos: bool,
        allowed_special: Union[Literal["all"], AbstractSet[str]] = set(),
        disallowed_special: Union[Literal["all"], Collection[str]] = (),
    )

        )

    def encode(
        self,
        s: str,
        *,
        bos: bool,
        eos: bool,
        allowed_special: Union[Literal["all"], AbstractSet[str]] = set(),
        disallowed_special: Union[Literal["all"], Collection[str]] = (),
    ) -> List[int]:
        """
        Encodes a string into a list of token IDs.

        Args:
            s (str): The input string to be encoded.
            bos (bool): Whether to prepend the beginning-of-sequence token.
            eos (bool): Whether to append the end-of-sequence token.
            allowed_tokens ("all"|set[str]): allowed special tokens in string
            disallowed_tokens ("all"|set[str]): special tokens that raise an error when in string

        Returns:
            list[int]: A list of token IDs.

        By default, setting disallowed_special=() encodes a string by ignoring
        special tokens. Specifically:
        - Setting `disallowed_special` to () will cause all text corresponding
          to special tokens to be encoded as natural text (insteading of raising
          an error).
        - Setting `allowed_special` to "all" will treat all text corresponding
          to special tokens to be encoded as special tokens.
        """
        assert type(s) is str

        # The tiktoken tokenizer can handle <=400k chars without
        # pyo3_runtime.PanicException.
        TIKTOKEN_MAX_ENCODE_CHARS = 400_000

        # https://github.com/openai/tiktoken/issues/195
        # Here we iterate over subsequences and split if we exceed the limit
        # of max consecutive non-whitespace or whitespace characters.
        MAX_NO_WHITESPACES_CHARS = 25_000

        substrs = (
            substr
            for i in range(0, len(s), TIKTOKEN_MAX_ENCODE_CHARS)
            for substr in self._split_whitespaces_or_nonwhitespaces(
                s[i : i + TIKTOKEN_MAX_ENCODE_CHARS], MAX_NO_WHITESPACES_CHARS
            )
        )
        t: List[int] = []
        for substr in substrs:
            t.extend(
                self.model.encode(
                    substr,
                    allowed_special=allowed_special,
                    disallowed_special=disallowed_special,
                )
            )
        if bos: