tokenization_utils_base

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase

Bases: SpecialTokensMixin

Base class for [PreTrainedTokenizer] and [PreTrainedTokenizerFast].

Handles shared (mostly boiler plate) methods for those two classes.

Source code in mindnlp/transformers/tokenization_utils_base.py

class PreTrainedTokenizerBase(SpecialTokensMixin):
    """
    Base class for [`PreTrainedTokenizer`] and [`PreTrainedTokenizerFast`].

    Handles shared (mostly boiler plate) methods for those two classes.
    """
    vocab_files_names: Dict[str, str] = {}
    pretrained_vocab_files_map: Dict[str, Dict[str, str]] = {}
    pretrained_init_configuration: Dict[str, Dict[str, Any]] = {}
    max_model_input_sizes: Dict[str, Optional[int]] = {}
    _auto_class: Optional[str] = None

    # first name has to correspond to main model input name
    # to make sure `tokenizer.pad(...)` works correctly
    model_input_names: List[str] = ["input_ids", "token_type_ids", "attention_mask"]
    padding_side: str = "right"
    truncation_side: str = "right"
    slow_tokenizer_class = None

    def __init__(self, **kwargs):
        r"""
        Initialize the PreTrainedTokenizerBase class.

        Args:
            self: The instance of the class.

        Returns:
            None.

        Raises:
            ValueError: If the provided padding_side or truncation_side is not one of ['right', 'left'].
        """
        # inputs and kwargs for saving and re-loading (see ``from_pretrained`` and ``save_pretrained``)
        self.init_inputs = ()
        self.init_kwargs = copy.deepcopy(kwargs)
        self.name_or_path = kwargs.pop("name_or_path", "")
        self._processor_class = kwargs.pop("processor_class", None)

        # For backward compatibility we fallback to set model_max_length from max_len if provided
        model_max_length = kwargs.pop("model_max_length", kwargs.pop("max_len", None))
        self.model_max_length = model_max_length if model_max_length is not None else VERY_LARGE_INTEGER

        # Padding and truncation side are right by default and overridden in subclasses. If specified in the kwargs, it
        # is changed.
        self.padding_side = kwargs.pop("padding_side", self.padding_side)
        if self.padding_side not in ["right", "left"]:
            raise ValueError(
                f"Padding side should be selected between 'right' and 'left', current value: {self.padding_side}"
            )

        self.truncation_side = kwargs.pop("truncation_side", self.truncation_side)
        if self.truncation_side not in ["right", "left"]:
            raise ValueError(
                f"Padding side should be selected between 'right' and 'left', current value: {self.truncation_side}"
            )

        self.model_input_names = kwargs.pop("model_input_names", self.model_input_names)

        # By default, cleaning tokenization spaces for both fast and slow tokenizers
        self.clean_up_tokenization_spaces = kwargs.pop("clean_up_tokenization_spaces", True)

        # By default, do not split special tokens for both fast and slow tokenizers
        self.split_special_tokens = kwargs.pop("split_special_tokens", False)

        self.deprecation_warnings = (
            {}
        )  # Use to store when we have already noticed a deprecation warning (avoid overlogging).
        self._in_target_context_manager = False

        # Stores a Jinja template that formats chat histories into tokenizable strings
        self.chat_template = kwargs.pop("chat_template", None)

        super().__init__(**kwargs)

    @property
    def max_len_single_sentence(self) -> int:
        """
        `int`: The maximum length of a sentence that can be fed to the model.
        """
        return self.model_max_length - self.num_special_tokens_to_add(pair=False)

    @property
    def max_len_sentences_pair(self) -> int:
        """
        `int`: The maximum combined length of a pair of sentences that can be fed to the model.
        """
        return self.model_max_length - self.num_special_tokens_to_add(pair=True)

    @max_len_single_sentence.setter
    def max_len_single_sentence(self, value) -> int:
        r"""
        This method 'max_len_single_sentence' in the class 'PreTrainedTokenizerBase'
        is used to set the maximum length of a single sentence in the tokenizer.

        Args:
            self (object): The instance of the PreTrainedTokenizerBase class.
            value (int): The value representing the maximum length of a single sentence.
                It is used to specify the maximum number of tokens allowed in a single sentence.

        Returns:
            int: Returns an integer value representing the maximum length of a single sentence that has been set.

        Raises:
            ValueError: Raised when attempting to set the 'max_len_single_sentence' parameter, as this functionality is deprecated.
                The value is now automatically configured by the tokenizer.
        """
        # For backward compatibility, allow to try to setup 'max_len_single_sentence'.
        if value == self.model_max_length - self.num_special_tokens_to_add(pair=False) and self.verbose:
            if not self.deprecation_warnings.get("max_len_single_sentence", False):
                logger.warning(
                    "Setting 'max_len_single_sentence' is now deprecated. This value is automatically set up."
                )
            self.deprecation_warnings["max_len_single_sentence"] = True
        else:
            raise ValueError(
                "Setting 'max_len_single_sentence' is now deprecated. This value is automatically set up."
            )

    @max_len_sentences_pair.setter
    def max_len_sentences_pair(self, value) -> int:
        r"""
        Sets the maximum length of a pair of sentences for tokenization and truncation.

        Args:
            self (PreTrainedTokenizerBase): The instance of the tokenizer.
            value (int): The desired maximum length of the sentence pair.

        Returns:
            int: The maximum length of the sentence pair.

        Raises:
            ValueError: If the specified value does not match the automatically set up length.

        Notes:
            This method is now deprecated and the value is automatically set up based on the model's maximum length and
            the number of special tokens added. If the value is equal to the model's maximum length minus the number
            of special tokens added, a deprecation warning is issued. Otherwise, a ValueError is raised.
        """
        # For backward compatibility, allow to try to setup 'max_len_sentences_pair'.
        if value == self.model_max_length - self.num_special_tokens_to_add(pair=True) and self.verbose:
            if not self.deprecation_warnings.get("max_len_sentences_pair", False):
                logger.warning(
                    "Setting 'max_len_sentences_pair' is now deprecated. This value is automatically set up."
                )
            self.deprecation_warnings["max_len_sentences_pair"] = True
        else:
            raise ValueError("Setting 'max_len_sentences_pair' is now deprecated. This value is automatically set up.")

    def _set_processor_class(self, processor_class: str):
        """Sets processor class as an attribute."""
        self._processor_class = processor_class

    @property
    def added_tokens_decoder(self) -> Dict[int, AddedToken]:
        r"""
        Method to retrieve the decoder mapping for added tokens.

        Args:
            self (PreTrainedTokenizerBase): The instance of the PreTrainedTokenizerBase class.
                It represents the tokenizer object for which the added tokens decoder is being retrieved.

        Returns:
            Dict[int, AddedToken]: A dictionary mapping integer indices to AddedToken objects.
                The AddedToken objects correspond to additional tokens that were added to the tokenizer.

        Raises:
            NotImplementedError: This exception is raised if the method is called and not implemented in the subclass.
        """
        raise NotImplementedError()

    def __repr__(self) -> str:
        r"""
        This method generates a string representation of the PreTrainedTokenizerBase object.

        Args:
            self: The instance of the PreTrainedTokenizerBase class.

        Returns:
            str:
                A string representing the object with various attributes such as
                name_or_path, vocab_size, model_max_length, is_fast, padding_side, truncation_side, special_tokens_map,
                clean_up_tokenization_spaces, and added_tokens_decoder.
                The added_tokens_decoder section includes a dictionary representation of added tokens and their respective values.

        Raises:
            None
        """
        added_tokens_decoder_rep = "\n\t".join([f"{k}: {v.__repr__()}," for k, v in self.added_tokens_decoder.items()])
        return (
            f"{self.__class__.__name__}(name_or_path='{self.name_or_path}',"
            f" vocab_size={self.vocab_size}, model_max_length={self.model_max_length}, is_fast={self.is_fast},"
            f" padding_side='{self.padding_side}', truncation_side='{self.truncation_side}',"
            f" special_tokens={self.special_tokens_map}, clean_up_tokenization_spaces={self.clean_up_tokenization_spaces}), "
            " added_tokens_decoder={\n\t" + added_tokens_decoder_rep + "\n}"
        )

    def __len__(self) -> int:
        r"""
        Method '__len__' in the class 'PreTrainedTokenizerBase'.

        Args:
            self: A reference to the instance of the class.
                It is automatically passed when the method is called. No additional arguments are expected.

        Returns:
            An integer value representing the length of the object.
                This method is intended to be overridden by subclasses to provide custom length calculation logic.

        Raises:
            NotImplementedError:
                This exception is raised to indicate that the method is not implemented in the current class
                and should be implemented in subclasses.
        """
        raise NotImplementedError()

    def get_vocab(self) -> Dict[str, int]:
        """
        Returns the vocabulary as a dictionary of token to index.

        `tokenizer.get_vocab()[token]` is equivalent to `tokenizer.convert_tokens_to_ids(token)` when `token` is in the
        vocab.

        Returns:
            `Dict[str, int]`: The vocabulary.
        """
        raise NotImplementedError()

    def apply_chat_template(
        self,
        conversation: Union[List[Dict[str, str]], "Conversation"],
        chat_template: Optional[str] = None,
        add_generation_prompt: bool = False,
        tokenize: bool = True,
        padding: bool = False,
        truncation: bool = False,
        max_length: Optional[int] = None,
        return_tensors: Optional[Union[str, TensorType]] = None,
        return_dict: bool = False,
        **tokenizer_kwargs,
    ) -> Union[str, List[int]]:
        """
        Converts a Conversation object or a list of dictionaries with `"role"` and `"content"` keys to a list of token
        ids. This method is intended for use with chat models, and will read the tokenizer's chat_template attribute to
        determine the format and control tokens to use when converting. When chat_template is None, it will fall back
        to the default_chat_template specified at the class level.

        Args:
            conversation (Union[List[Dict[str, str]], "Conversation"]): A Conversation object or list of dicts
                with "role" and "content" keys, representing the chat history so far.
            chat_template (str, *optional*): A Jinja template to use for this conversion. If
                this is not passed, the model's default chat template will be used instead.
            add_generation_prompt (bool, *optional*): Whether to end the prompt with the token(s) that indicate
                the start of an assistant message. This is useful when you want to generate a response from the model.
                Note that this argument will be passed to the chat template, and so it must be supported in the
                template for this argument to have any effect.
            tokenize (`bool`, defaults to `True`):
                Whether to tokenize the output. If `False`, the output will be a string.
            padding (`bool`, defaults to `False`):
                Whether to pad sequences to the maximum length. Has no effect if tokenize is `False`.
            truncation (`bool`, defaults to `False`):
                Whether to truncate sequences at the maximum length. Has no effect if tokenize is `False`.
            max_length (`int`, *optional*):
                Maximum length (in tokens) to use for padding or truncation. Has no effect if tokenize is `False`. If
                not specified, the tokenizer's `max_length` attribute will be used as a default.
            return_tensors (`str` or [`~utils.TensorType`], *optional*):
                If set, will return tensors of a particular framework. Has no effect if tokenize is `False`. Acceptable
                values are:

                - `'tf'`: Return TensorFlow `tf.Tensor` objects.
                - `'pt'`: Return PyTorch `mindspore.Tensor` objects.
                - `'np'`: Return NumPy `np.ndarray` objects.
                - `'jax'`: Return JAX `jnp.ndarray` objects.
            **tokenizer_kwargs: Additional kwargs to pass to the tokenizer.

        Returns:
            `List[int]`: A list of token ids representing the tokenized chat so far, including control tokens. This
            output is ready to pass to the model, either directly or via methods like `generate()`.
        """
        if hasattr(conversation, "messages"):
            # Indicates it's a Conversation object
            conversation = conversation.messages

        # priority: `chat_template` argument > `tokenizer.chat_template` > `tokenizer.default_chat_template`
        if chat_template is None:
            if self.chat_template is not None:
                chat_template = self.chat_template
            else:
                chat_template = self.default_chat_template

        # Compilation function uses a cache to avoid recompiling the same template
        compiled_template = self._compile_jinja_template(chat_template)

        rendered = compiled_template.render(
            messages=conversation, add_generation_prompt=add_generation_prompt, **self.special_tokens_map
        )

        if padding is True:
            padding = "max_length"  # There's only one sequence here, so "longest" makes no sense
        if tokenize:
            if return_dict:
                return self(
                    rendered,
                    padding=padding,
                    truncation=truncation,
                    max_length=max_length,
                    add_special_tokens=False,
                    return_tensors=return_tensors,
                    **tokenizer_kwargs,
                )

            return self.encode(
                rendered,
                padding=padding,
                truncation=truncation,
                max_length=max_length,
                add_special_tokens=False,
                return_tensors=return_tensors,
                **tokenizer_kwargs,
            )
        return rendered

    @lru_cache(128)
    def _compile_jinja_template(self, chat_template):
        r"""
        Compiles a Jinja template for chat messages.

        Args:
            self (PreTrainedTokenizerBase): An instance of the PreTrainedTokenizerBase class.
            chat_template (str): The Jinja template for chat messages.

        Returns:
            None

        Raises:
            ImportError: If jinja2 is not installed.
            TemplateError: If there is an error in the Jinja template.

        This method takes a Jinja template for chat messages and compiles it into a Jinja environment.
        The template is then ready to be used for rendering chat messages.
        The method uses an LRU cache with a maximum size of 128 to store compiled templates,
        which provides a performance boost when the same template is used multiple times.

        The method first checks if jinja2 is installed by trying to import the necessary modules.
        If jinja2 is not installed, an ImportError is raised with a helpful error message.
        If jinja2 is installed, an ImmutableSandboxedEnvironment is created with the trim_blocks and lstrip_blocks options set to True.
        This environment ensures that the template is rendered safely and without any leading or trailing white spaces.

        The method also defines a local function named raise_exception, which is used to raise a TemplateError with a custom error message.
        This function is added to the Jinja environment's globals under the name 'raise_exception'.
        This allows the template to raise an error by calling the 'raise_exception' function with an error message as an argument.

        Finally, the method compiles the chat_template into a Jinja template using the from_string method of the Jinja environment.
        The compiled template is then returned for further use.
        """
        try:
            from jinja2.exceptions import TemplateError
            from jinja2.sandbox import ImmutableSandboxedEnvironment
        except ImportError as exc:
            raise ImportError("apply_chat_template requires jinja2 to be installed.") from exc

        def raise_exception(message):
            raise TemplateError(message)

        jinja_env = ImmutableSandboxedEnvironment(trim_blocks=True, lstrip_blocks=True)
        jinja_env.globals["raise_exception"] = raise_exception
        return jinja_env.from_string(chat_template)

    @property
    def default_chat_template(self):
        """
        This template formats inputs in the standard ChatML format. See
        https://github.com/openai/openai-python/blob/main/chatml.md
        """
        logger.warning_once(
            "\nNo chat template is defined for this tokenizer - using a default chat template "
            "that implements the ChatML format. If the default is not appropriate for "
            "your model, please set `tokenizer.chat_template` to an appropriate template. "
            "See https://hf-mirror.com/docs/transformers/main/chat_templating for more information.\n"
        )
        return (
            "{% for message in messages %}"
            "{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}"
            "{% endfor %}"
            "{% if add_generation_prompt %}"
            "{{ '<|im_start|>assistant\n' }}"
            "{% endif %}"
        )

    @classmethod
    def from_pretrained(
        cls,
        pretrained_model_name_or_path: Union[str, os.PathLike],
        *init_inputs,
        cache_dir: Optional[Union[str, os.PathLike]] = None,
        force_download: bool = False,
        local_files_only: bool = False,
        token: str = None,
        mirror: str = 'huggingface',
        **kwargs,
    ):
        r"""
        Instantiate a [`~tokenization_utils_base.PreTrainedTokenizerBase`] (or a derived class) from a predefined
        tokenizer.

        Args:
            pretrained_model_name_or_path (`str` or `os.PathLike`):
                Can be either:

                - A string, the *model id* of a predefined tokenizer hosted inside a model repo on hf-mirror.com.
                  Valid model ids can be located at the root-level, like `bert-base-uncased`, or namespaced under a
                  user or organization name, like `dbmdz/bert-base-german-cased`.
                - A path to a *directory* containing vocabulary files required by the tokenizer, for instance saved
                  using the [`~tokenization_utils_base.PreTrainedTokenizerBase.save_pretrained`] method, e.g.,
                  `./my_model_directory/`.
                - (**Deprecated**, not applicable to all derived classes) A path or url to a single saved vocabulary
                  file (if and only if the tokenizer only requires a single vocabulary file like Bert or XLNet), e.g.,
                  `./my_model_directory/vocab.txt`.
            cache_dir (`str` or `os.PathLike`, *optional*):
                Path to a directory in which a downloaded predefined tokenizer vocabulary files should be cached if the
                standard cache should not be used.
            force_download (`bool`, *optional*, defaults to `False`):
                Whether or not to force the (re-)download the vocabulary files and override the cached versions if they
                exist.
            resume_download (`bool`, *optional*, defaults to `False`):
                Whether or not to delete incompletely received files. Attempt to resume the download if such a file
                exists.
            proxies (`Dict[str, str]`, *optional*):
                A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128',
                'http://hostname': 'foo.bar:4012'}`. The proxies are used on each request.
            token (`str` or *bool*, *optional*):
                The token to use as HTTP bearer authorization for remote files. If `True`, will use the token generated
                when running `huggingface-cli login` (stored in `~/.huggingface`).
            local_files_only (`bool`, *optional*, defaults to `False`):
                Whether or not to only rely on local files and not to attempt to download any files.
            revision (`str`, *optional*, defaults to `"main"`):
                The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a
                git-based system for storing models and other artifacts on hf-mirror.com, so `revision` can be any
                identifier allowed by git.
            subfolder (`str`, *optional*):
                In case the relevant files are located inside a subfolder of the model repo on hf-mirror.com (e.g. for
                facebook/rag-token-base), specify it here.
            inputs (additional positional arguments, *optional*):
                Will be passed along to the Tokenizer `__init__` method.
            kwargs (additional keyword arguments, *optional*):
                Will be passed to the Tokenizer `__init__` method. Can be used to set special tokens like `bos_token`,
                `eos_token`, `unk_token`, `sep_token`, `pad_token`, `cls_token`, `mask_token`,
                `additional_special_tokens`. See parameters in the `__init__` for more details.

        <Tip>

        Passing `token=True` is required when you want to use a private model.

        </Tip>

        Example:
            ```python
            >>> # We can't instantiate directly the base class *PreTrainedTokenizerBase* so let's show our examples on a derived class: BertTokenizer
            >>> # Download vocabulary from hf-mirror.com and cache.
            >>> tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
            ...
            >>> # Download vocabulary from hf-mirror.com (user-uploaded) and cache.
            >>> tokenizer = BertTokenizer.from_pretrained("dbmdz/bert-base-german-cased")
            ...
            >>> # If vocabulary files are in a directory (e.g. tokenizer was saved using *save_pretrained('./test/saved_model/')*)
            >>> tokenizer = BertTokenizer.from_pretrained("./test/saved_model/")
            ...
            >>> # If the tokenizer uses a single vocabulary file, you can point directly to this file
            >>> tokenizer = BertTokenizer.from_pretrained("./test/saved_model/my_vocab.txt")
            ...
            >>> # You can link tokens to special vocabulary when instantiating
            >>> tokenizer = BertTokenizer.from_pretrained("bert-base-uncased", unk_token="<unk>")
            >>> # You should be sure '<unk>' is in the vocabulary when doing that.
            >>> # Otherwise use tokenizer.add_special_tokens({'unk_token': '<unk>'}) instead)
            >>> assert tokenizer.unk_token == "<unk>"
            ```
        """
        resume_download = kwargs.pop("resume_download", False)
        proxies = kwargs.pop("proxies", None)
        subfolder = kwargs.pop("subfolder", None)
        revision = kwargs.pop("revision", "main")

        if is_offline_mode() and not local_files_only:
            logger.info("Offline mode: forcing local_files_only=True")
            local_files_only = True

        pretrained_model_name_or_path = str(pretrained_model_name_or_path)
        vocab_files = {}
        init_configuration = {}

        is_local = os.path.isdir(pretrained_model_name_or_path)
        single_file_id = None
        if os.path.isfile(pretrained_model_name_or_path) or is_remote_url(pretrained_model_name_or_path):
            if len(cls.vocab_files_names) > 1:
                raise ValueError(
                    f"Calling {cls.__name__}.from_pretrained() with the path to a single file or url is not "
                    "supported for this tokenizer. Use a model identifier or the path to a directory instead."
                )
            warnings.warn(
                f"Calling {cls.__name__}.from_pretrained() with the path to a single file or url is deprecated and "
                "won't be possible anymore in v5. Use a model identifier or the path to a directory instead.",
                FutureWarning,
            )
            file_id = list(cls.vocab_files_names.keys())[0]

            vocab_files[file_id] = pretrained_model_name_or_path
            single_file_id = file_id
        else:
            # At this point pretrained_model_name_or_path is either a directory or a model identifier name
            additional_files_names = {
                "added_tokens_file": ADDED_TOKENS_FILE,  # kept only for legacy
                "special_tokens_map_file": SPECIAL_TOKENS_MAP_FILE,  # kept only for legacy
                "tokenizer_config_file": TOKENIZER_CONFIG_FILE,
                # tokenizer_file used to initialize a slow from a fast. Properly copy the `addedTokens` instead of adding in random orders
                "tokenizer_file": FULL_TOKENIZER_FILE,
            }
            vocab_files = {**cls.vocab_files_names, **additional_files_names}
            if "tokenizer_file" in vocab_files:
                # Try to get the tokenizer config to see if there are versioned tokenizer files.
                fast_tokenizer_file = FULL_TOKENIZER_FILE
                resolved_config_file = cached_file(
                    pretrained_model_name_or_path,
                    TOKENIZER_CONFIG_FILE,
                    cache_dir=cache_dir,
                    force_download=force_download,
                    resume_download=resume_download,
                    proxies=proxies,
                    local_files_only=local_files_only,
                    token=token,
                    subfolder=subfolder,
                    revision=revision,
                    mirror=mirror,
                    _raise_exceptions_for_missing_entries=False,
                    _raise_exceptions_for_connection_errors=False,
                )
                if resolved_config_file is not None:
                    with open(resolved_config_file, encoding="utf-8") as reader:
                        tokenizer_config = json.load(reader)
                        if "fast_tokenizer_files" in tokenizer_config:
                            fast_tokenizer_file = get_fast_tokenizer_file(tokenizer_config["fast_tokenizer_files"])
                vocab_files["tokenizer_file"] = fast_tokenizer_file

        # Get files from url, cache, or disk depending on the case
        resolved_vocab_files = {}
        unresolved_files = []
        for file_id, file_path in vocab_files.items():
            if file_path is None:
                resolved_vocab_files[file_id] = None
            elif single_file_id == file_id:
                if os.path.isfile(file_path):
                    resolved_vocab_files[file_id] = file_path
                elif is_remote_url(file_path):
                    resolved_vocab_files[file_id] = download_url(file_path, proxies=proxies)
            else:
                resolved_vocab_files[file_id] = cached_file(
                    pretrained_model_name_or_path,
                    file_path,
                    cache_dir=cache_dir,
                    force_download=force_download,
                    proxies=proxies,
                    resume_download=resume_download,
                    local_files_only=local_files_only,
                    token=token,
                    subfolder=subfolder,
                    revision=revision,
                    mirror=mirror,
                    _raise_exceptions_for_missing_entries=False,
                    _raise_exceptions_for_connection_errors=False,
                )
        if len(unresolved_files) > 0:
            logger.info(
                f"Can't load following files from cache: {unresolved_files} and cannot check if these "
                "files are necessary for the tokenizer to operate."
            )

        if all(full_file_name is None for full_file_name in resolved_vocab_files.values()):
            raise EnvironmentError(
                f"Can't load tokenizer for '{pretrained_model_name_or_path}'. If you were trying to load it from "
                "'https://hf-mirror.com/models', make sure you don't have a local directory with the same name. "
                f"Otherwise, make sure '{pretrained_model_name_or_path}' is the correct path to a directory "
                f"containing all relevant files for a {cls.__name__} tokenizer."
            )

        for file_id, file_path in vocab_files.items():
            if file_id not in resolved_vocab_files:
                continue

            if is_local:
                logger.info(f"loading file {file_path}")
            else:
                logger.info(f"loading file {file_path} from cache at {resolved_vocab_files[file_id]}")

        return cls._from_pretrained(
            resolved_vocab_files,
            pretrained_model_name_or_path,
            init_configuration,
            *init_inputs,
            cache_dir=cache_dir,
            local_files_only=local_files_only,
            _is_local=is_local,
            **kwargs,
        )

    @classmethod
    def _from_pretrained(
        cls,
        resolved_vocab_files,
        pretrained_model_name_or_path,
        init_configuration,
        *init_inputs,
        token=None,
        cache_dir=None,
        local_files_only=False,
        _is_local=False,
        **kwargs,
    ):
        r"""
        This method initializes a PreTrainedTokenizerBase from a pretrained model or from a set of resolved vocabulary files.

        Args:
            cls (class): The class of the tokenizer instance.
            resolved_vocab_files (dict): A dictionary containing the resolved vocabulary files.
            pretrained_model_name_or_path (str): The name or path of the pretrained model.
            init_configuration (dict): The initial configuration for the tokenizer.
            *init_inputs: Additional positional arguments for initializing the tokenizer.
            token (str, optional): A token for the tokenizer. Default is None.
            cache_dir (str, optional): The directory to cache the tokenizer files. Default is None.
            local_files_only (bool, optional): If True, only use local files. Default is False.
            _is_local (bool, optional): If True, the files are local. Default is False.
            **kwargs: Additional keyword arguments for initializing the tokenizer.

        Returns:
            None.

        Raises:
            OSError: If unable to load vocabulary from file. Please check that the provided vocabulary is accessible
                and not corrupted.
            ValueError: If there is a mismatch in the added tokens decoder format.
            Warning: If special tokens have been added in the vocabulary, it advises to make sure the associated
                word embeddings are fine-tuned or trained.
            """
        # We instantiate fast tokenizers based on a slow tokenizer if we don't have access to the tokenizer.json
        # file or if `from_slow` is set to True.
        from_slow = kwargs.get("from_slow", False)
        has_tokenizer_file = resolved_vocab_files.get("tokenizer_file", None) is not None
        if (from_slow or not has_tokenizer_file) and cls.slow_tokenizer_class is not None:
            slow_tokenizer = (cls.slow_tokenizer_class)._from_pretrained(
                copy.deepcopy(resolved_vocab_files),
                pretrained_model_name_or_path,
                copy.deepcopy(init_configuration),
                *init_inputs,
                token=token,
                cache_dir=cache_dir,
                local_files_only=local_files_only,
                **(copy.deepcopy(kwargs)),
            )
        else:
            slow_tokenizer = None

        # Prepare tokenizer initialization kwargs
        # Did we saved some inputs and kwargs to reload ?
        tokenizer_config_file = resolved_vocab_files.pop("tokenizer_config_file", None)
        if tokenizer_config_file is not None:
            with open(tokenizer_config_file, encoding="utf-8") as tokenizer_config_handle:
                init_kwargs = json.load(tokenizer_config_handle)
            # First attempt. We get tokenizer_class from tokenizer_config to check mismatch between tokenizers.
            config_tokenizer_class = init_kwargs.get("tokenizer_class")
            init_kwargs.pop("tokenizer_class", None)
            if not has_tokenizer_file:
                init_kwargs.pop("tokenizer_file", None)
            saved_init_inputs = init_kwargs.pop("init_inputs", ())
            if not init_inputs:
                init_inputs = saved_init_inputs
        else:
            config_tokenizer_class = None
            init_kwargs = init_configuration

        if config_tokenizer_class is None:
            from .models.auto.configuration_auto import AutoConfig  # tests_ignore

            # Second attempt. If we have not yet found tokenizer_class, let's try to use the config.
            try:
                config = AutoConfig.from_pretrained(
                    pretrained_model_name_or_path,
                    token=token,
                    cache_dir=cache_dir,
                    local_files_only=local_files_only,
                )
                config_tokenizer_class = config.tokenizer_class
            except (OSError, ValueError, KeyError):
                # skip if an error occurred.
                config = None
            if config_tokenizer_class is None:
                # Third attempt. If we have not yet found the original type of the tokenizer,
                # we are loading we see if we can infer it from the type of the configuration file
                from .models.auto.tokenization_auto import TOKENIZER_MAPPING_NAMES  # tests_ignore

                if hasattr(config, "model_type"):
                    model_type = config.model_type
                else:
                    # Fallback: use pattern matching on the string.
                    model_type = None
                    for pattern in TOKENIZER_MAPPING_NAMES.keys():
                        if pattern in str(pretrained_model_name_or_path):
                            model_type = pattern
                            break

                if model_type is not None:
                    config_tokenizer_class, config_tokenizer_class_fast = TOKENIZER_MAPPING_NAMES.get(
                        model_type, (None, None)
                    )
                    if config_tokenizer_class is None:
                        config_tokenizer_class = config_tokenizer_class_fast

        if config_tokenizer_class is not None:
            if cls.__name__.replace("Fast", "") != config_tokenizer_class.replace("Fast", ""):
                logger.warning(
                    "The tokenizer class you load from this checkpoint is not the same type as the class this"
                    " function is called from. It may result in unexpected tokenization. \nThe tokenizer class you"
                    f" load from this checkpoint is '{config_tokenizer_class}'. \nThe class this function is called"
                    f" from is '{cls.__name__}'."
                )

        # Update with newly provided kwargs
        init_kwargs.update(kwargs)

        # Set max length if needed
        if pretrained_model_name_or_path in cls.max_model_input_sizes:
            # if we're using a pretrained model, ensure the tokenizer
            # wont index sequences longer than the number of positional embeddings

            model_max_length = cls.max_model_input_sizes[pretrained_model_name_or_path]
            if model_max_length is not None and isinstance(model_max_length, (int, float)):
                model_max_length = min(init_kwargs.get("model_max_length", int(1e30)), model_max_length)
                # TODO(PVP) - uncomment following line in Transformers v5
                # init_kwargs["model_max_length"] = model_max_length
                # TODO(PVP) - remove in Transformers v5
                # ---
                init_kwargs["model_max_length"] = cls._eventually_correct_t5_max_length(
                    pretrained_model_name_or_path, model_max_length, init_kwargs.get("model_max_length")
                )
                # ---

        # Merge resolved_vocab_files arguments in init_kwargs.
        added_tokens_file = resolved_vocab_files.pop("added_tokens_file", None)
        special_tokens_map_file = resolved_vocab_files.pop("special_tokens_map_file", None)
        for args_name, file_path in resolved_vocab_files.items():
            if args_name not in init_kwargs:
                init_kwargs[args_name] = file_path
        tokenizer_file = resolved_vocab_files.pop("tokenizer_file", None)

        if slow_tokenizer is not None:
            init_kwargs["__slow_tokenizer"] = slow_tokenizer
        init_kwargs["name_or_path"] = pretrained_model_name_or_path

        #### Handle tokenizer serialization of added and special tokens
        added_tokens_decoder: Dict[int, AddedToken] = {}
        added_tokens_map: Dict[str, AddedToken] = {}
        # if we have info on the slow added tokens
        if "added_tokens_decoder" in init_kwargs:
            for idx, token in init_kwargs["added_tokens_decoder"].items():
                if isinstance(token, dict):
                    token = AddedToken(**token)
                if isinstance(token, AddedToken):
                    added_tokens_decoder[int(idx)] = token
                    added_tokens_map[str(token)] = token
                else:
                    raise ValueError(
                        f"Found a {token.__class__} in the saved `added_tokens_decoder`, should be a dictionary or an AddedToken instance"
                    )
        else:
            # begin legacy: read the added_tokens_file and update kwargs with special_tokens_map if modified
            if special_tokens_map_file is not None:
                with open(special_tokens_map_file, encoding="utf-8") as special_tokens_map_handle:
                    special_tokens_map = json.load(special_tokens_map_handle)
                    for key, value in special_tokens_map.items():
                        if key in kwargs and kwargs[key]:
                            # This value has already been redefined by the kwargs
                            # We keep this new value and ignore the one stored in the special_tokens_map_file
                            continue
                        if isinstance(value, dict):
                            value = AddedToken(**value, special=True)
                        elif key == "additional_special_tokens" and isinstance(value, list):
                            additional_special_tokens = init_kwargs.pop("additional_special_tokens", []) or []
                            for token in value:
                                token = AddedToken(**token, special=True) if isinstance(token, dict) else token
                                if token not in additional_special_tokens:
                                    additional_special_tokens.append(token)
                            value = additional_special_tokens
                        init_kwargs[key] = value

            # slow -> slow|fast, legacy: convert the `"added_tokens.json"` file to `added_tokens_decoder`.
            # this is for legacy purpose. We don't add the tokens after init for efficiency.
            if added_tokens_file is not None:
                special_tokens = []
                for key in cls.SPECIAL_TOKENS_ATTRIBUTES & init_kwargs.keys():
                    if init_kwargs[key] is not None:
                        if key == "additional_special_tokens":
                            special_tokens += [str(token) for token in init_kwargs[key]]
                        else:
                            special_tokens.append(str(init_kwargs[key]))

                with open(added_tokens_file, encoding="utf-8") as added_tokens_handle:
                    added_tok_encoder = json.load(added_tokens_handle)
                for str_token, index in added_tok_encoder.items():
                    # if index not in added_tokens_decoder and str_token not in added_tokens_map:
                    special = str_token in special_tokens
                    added_tokens_decoder[index] = AddedToken(
                        str_token, rstrip=False, lstrip=False, normalized=not special, special=special
                    )
                    added_tokens_map[str(token)] = added_tokens_decoder[index]

            # allows converting a fast -> slow: add the `tokenizer.json`'s `"added_tokens"` to the slow tokenizer
            # if `tokenizer_config.json` is `None`
            if "Fast" not in cls.__name__ and tokenizer_file is not None:
                # This is for slow so can be done before
                with open(tokenizer_file, encoding="utf-8") as tokenizer_file_handle:
                    tokenizer_file_handle = json.load(tokenizer_file_handle)
                    added_tokens = tokenizer_file_handle.pop("added_tokens")
                for serialized_tokens in added_tokens:
                    idx = serialized_tokens.pop("id")
                    added_tokens_decoder[idx] = AddedToken(**serialized_tokens)
                    added_tokens_map[str(added_tokens_decoder[idx])] = added_tokens_decoder[idx]
            # end legacy

        # Passing AddedTokens and not strings to the class to prevent it from casting the string to a different AddedToken
        for key in cls.SPECIAL_TOKENS_ATTRIBUTES & init_kwargs.keys():
            if added_tokens_map and init_kwargs[key] is not None:
                if key != "additional_special_tokens":
                    init_kwargs[key] = added_tokens_map.get(str(init_kwargs[key]), init_kwargs[key])

        init_kwargs["added_tokens_decoder"] = added_tokens_decoder
        # convert {'__type': 'AddedToken', 'content': '<ent>', 'lstrip': False, 'normalized': True, ...} to AddedTokens
        init_kwargs = cls.convert_added_tokens(init_kwargs, save=False)
        # Instantiate the tokenizer.
        try:
            tokenizer = cls(*init_inputs, **init_kwargs)
        except OSError as exc:
            raise OSError(
                "Unable to load vocabulary from file. "
                "Please check that the provided vocabulary is accessible and not corrupted."
            ) from exc

        if added_tokens_decoder and max(list(added_tokens_decoder.keys())[-1], 0) > tokenizer.vocab_size:
            logger.warning_advice(
                "Special tokens have been added in the vocabulary, make sure the associated word embeddings are"
                " fine-tuned or trained."
            )
        return tokenizer

    @staticmethod
    def _eventually_correct_t5_max_length(pretrained_model_name_or_path, max_model_length, init_max_model_length):
        r"""
        This method sets the maximum model length for a pretrained T5 model.

        Args:
            pretrained_model_name_or_path (str): The name or path of the pretrained T5 model.
            max_model_length (int): The maximum model length to be set.
            init_max_model_length (int): The initial maximum model length.

        Returns:
            None.

        Raises:
            TypeError: If the input parameters are not of the correct type.
            ValueError: If max_model_length or init_max_model_length is less than or equal to 0.
        """
        # This method should be deleted in Transformers v5
        # Its only purpose is to potentially throw a warning
        # that incorrectly defined max lengths of T5's tokenizer are used
        # which we will correct in Transformers v5.
        return max_model_length

    @classmethod
    def convert_added_tokens(cls, obj: Union[AddedToken, Any], save=False, add_type_field=True):
        r"""
        Converts AddedToken objects to dictionaries and vice versa.

        Args:
            cls (type): The class reference.
            obj (Union[AddedToken, Any]):
                The object to convert. Can be an AddedToken object, dictionary, list, tuple, or any other type.
            save (bool): Indicates whether to save the converted object. Default is False.
            add_type_field (bool): Indicates whether to add a '__type' field during conversion. Default is True.

        Returns:
            None: The method modifies the input object in place or returns a converted object.

        Raises:
            TypeError: If the obj parameter is of an unsupported type.
            KeyError: If the '__type' key is not found in the dictionary object.
        """
        if isinstance(obj, dict) and "__type" in obj and obj["__type"] == "AddedToken":
            obj.pop("__type")
            return AddedToken(**obj)
        if isinstance(obj, AddedToken) and save:
            obj = obj.__getstate__()
            if add_type_field:
                obj["__type"] = "AddedToken"
            else:
                # Don't save "special" for previous tokenizers
                obj.pop("special")
            return obj
        if isinstance(obj, (list, tuple)):
            return [cls.convert_added_tokens(o, save=save, add_type_field=add_type_field) for o in obj]
        if isinstance(obj, dict):
            return {k: cls.convert_added_tokens(v, save=save, add_type_field=add_type_field) for k, v in obj.items()}
        return obj

    def save_pretrained(
        self,
        save_directory: Union[str, os.PathLike],
        legacy_format: Optional[bool] = None,
        filename_prefix: Optional[str] = None,
        push_to_hub: bool = False,
        **kwargs,
    ) -> Tuple[str]:
        """
        Save the full tokenizer state.

        This method make sure the full tokenizer can then be re-loaded using the
        [`~tokenization_utils_base.PreTrainedTokenizer.from_pretrained`] class method..

        Warning,None This won't save modifications you may have applied to the tokenizer after the instantiation (for
        instance, modifying `tokenizer.do_lower_case` after creation).

        Args:
            save_directory (`str` or `os.PathLike`): The path to a directory where the tokenizer will be saved.
            legacy_format (`bool`, *optional*):
                Only applicable for a fast tokenizer. If unset (default), will save the tokenizer in the unified JSON
                format as well as in legacy format if it exists, i.e. with tokenizer specific vocabulary and a separate
                added_tokens files.

                If `False`, will only save the tokenizer in the unified JSON format. This format is incompatible with
                "slow" tokenizers (not powered by the *tokenizers* library), so the tokenizer will not be able to be
                loaded in the corresponding "slow" tokenizer.

                If `True`, will save the tokenizer in legacy format. If the "slow" tokenizer doesn't exits, a value
                error is raised.
            filename_prefix (`str`, *optional*):
                A prefix to add to the names of the files saved by the tokenizer.
            push_to_hub (`bool`, *optional*, defaults to `False`):
                Whether or not to push your model to the Hugging Face model hub after saving it. You can specify the
                repository you want to push to with `repo_id` (will default to the name of `save_directory` in your
                namespace).
            kwargs (`Dict[str, Any]`, *optional*):
                Additional key word arguments passed along to the [`~utils.PushToHubMixin.push_to_hub`] method.

        Returns:
            A tuple of `str`: The files saved.
        """
        use_auth_token = kwargs.pop("use_auth_token", None)

        if use_auth_token is not None:
            warnings.warn(
                "The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.",
                FutureWarning,
            )
            if kwargs.get("token", None) is not None:
                raise ValueError(
                    "`token` and `use_auth_token` are both specified. Please set only the argument `token`."
                )
            kwargs["token"] = use_auth_token

        if os.path.isfile(save_directory):
            logger.error(f"Provided path ({save_directory}) should be a directory, not a file")
            return

        os.makedirs(save_directory, exist_ok=True)

        if push_to_hub:
            repo_id = kwargs.pop("repo_id", save_directory.split(os.path.sep)[-1])
            repo_id = self._create_repo(repo_id, **kwargs)

        special_tokens_map_file = os.path.join(
            save_directory, (filename_prefix + "-" if filename_prefix else "") + SPECIAL_TOKENS_MAP_FILE
        )
        tokenizer_config_file = os.path.join(
            save_directory, (filename_prefix + "-" if filename_prefix else "") + TOKENIZER_CONFIG_FILE
        )

        tokenizer_config = copy.deepcopy(self.init_kwargs)

        # Let's save the init kwargs
        target_keys = set(self.init_kwargs.keys())
        # Let's save the special tokens map (only the strings)
        target_keys.update(["model_max_length", "clean_up_tokenization_spaces"])

        for k in target_keys:
            if hasattr(self, k):
                tokenizer_config[k] = getattr(self, k)

        # Let's make sure we properly save the special tokens.
        tokenizer_config.update(self.special_tokens_map)

        if self.chat_template is not None:
            tokenizer_config["chat_template"] = self.chat_template

        if len(self.init_inputs) > 0:
            tokenizer_config["init_inputs"] = copy.deepcopy(self.init_inputs)
        for file_id in self.vocab_files_names.keys():
            tokenizer_config.pop(file_id, None)

        # no typefields, this way old fast and slow can load it
        tokenizer_config = self.convert_added_tokens(tokenizer_config, add_type_field=True, save=True)

        # Process added tokens seperatly: allows previous versions to ignore it!
        added_tokens = {}
        for key, value in self.added_tokens_decoder.items():
            added_tokens[key] = value.__getstate__()
        tokenizer_config["added_tokens_decoder"] = added_tokens

        # Add tokenizer class to the tokenizer config to be able to reload it with from_pretrained
        tokenizer_class = self.__class__.__name__
        # Remove the Fast at the end unless we have a special `PreTrainedTokenizerFast`
        if tokenizer_class.endswith("Fast") and tokenizer_class != "PreTrainedTokenizerFast":
            tokenizer_class = tokenizer_class[:-4]
        tokenizer_config["tokenizer_class"] = tokenizer_class
        if getattr(self, "_auto_map", None) is not None:
            tokenizer_config["auto_map"] = self._auto_map
        if getattr(self, "_processor_class", None) is not None:
            tokenizer_config["processor_class"] = self._processor_class

        # remove private information
        if "name_or_path" in tokenizer_config:
            tokenizer_config.pop("name_or_path")
            tokenizer_config.pop("special_tokens_map_file", None)
            tokenizer_config.pop("tokenizer_file", None)

        with open(tokenizer_config_file, "w", encoding="utf-8") as f:
            out_str = json.dumps(tokenizer_config, indent=2, sort_keys=True, ensure_ascii=False) + "\n"
            f.write(out_str)
        logger.info(f"tokenizer config file saved in {tokenizer_config_file}")

        # Sanitize AddedTokens in special_tokens_map

        # kept for forward compatibility, will be removed in transoformers 5. Typefields are not saved for FC, special should not be save either
        write_dict = self.convert_added_tokens(self.special_tokens_map_extended, save=True, add_type_field=False)
        with open(special_tokens_map_file, "w", encoding="utf-8") as f:
            out_str = json.dumps(write_dict, indent=2, sort_keys=True, ensure_ascii=False) + "\n"
            f.write(out_str)
        logger.info(f"Special tokens file saved in {special_tokens_map_file}")

        file_names = (tokenizer_config_file, special_tokens_map_file)

        save_files = self._save_pretrained(
            save_directory=save_directory,
            file_names=file_names,
            legacy_format=legacy_format,
            filename_prefix=filename_prefix,
        )

        return save_files

    def _save_pretrained(
        self,
        save_directory: Union[str, os.PathLike],
        file_names: Tuple[str],
        legacy_format: Optional[bool] = None,
        filename_prefix: Optional[str] = None,
    ) -> Tuple[str]:
        """
        Save a tokenizer using the slow-tokenizer/legacy format: vocabulary + added tokens.

        Fast tokenizers can also be saved in a unique JSON file containing {config + vocab + added-tokens} using the
        specific [`~tokenization_utils_fast.PreTrainedTokenizerFast._save_pretrained`]
        """
        if legacy_format is False:
            raise ValueError(
                "Only fast tokenizers (instances of PreTrainedTokenizerFast) can be saved in non legacy format."
            )

        save_directory = str(save_directory)

        added_tokens_file = os.path.join(
            save_directory, (filename_prefix + "-" if filename_prefix else "") + ADDED_TOKENS_FILE
        )
        # the new get_added_vocab() also returns special tokens and tokens that have an index < vocab_size
        added_vocab = {tok: index for tok, index in self.added_tokens_encoder.items() if index >= self.vocab_size}
        if added_vocab:
            with open(added_tokens_file, "w", encoding="utf-8") as f:
                out_str = json.dumps(added_vocab, indent=2, sort_keys=True, ensure_ascii=False) + "\n"
                f.write(out_str)
                logger.info(f"added tokens file saved in {added_tokens_file}")

        vocab_files = self.save_vocabulary(save_directory, filename_prefix=filename_prefix)

        return file_names + vocab_files + (added_tokens_file,)

    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
        """
        Save only the vocabulary of the tokenizer (vocabulary + added tokens).

        This method won't save the configuration and special token mappings of the tokenizer. Use
        [`~PreTrainedTokenizerFast._save_pretrained`] to save the whole state of the tokenizer.

        Args:
            save_directory (`str`):
                The directory in which to save the vocabulary.
            filename_prefix (`str`, *optional*):
                An optional prefix to add to the named of the saved files.

        Returns:
            `Tuple(str)`: Paths to the files saved.
        """
        raise NotImplementedError

    def tokenize(self, text: str, pair: Optional[str] = None, add_special_tokens: bool = False, **kwargs) -> List[str]:
        """
        Converts a string in a sequence of tokens, replacing unknown tokens with the `unk_token`.

        Args:
            text (`str`):
                The sequence to be encoded.
            pair (`str`, *optional*):
                A second sequence to be encoded with the first.
            add_special_tokens (`bool`, *optional*, defaults to `False`):
                Whether or not to add the special tokens associated with the corresponding model.
            kwargs (additional keyword arguments, *optional*):
                Will be passed to the underlying model specific encode method. See details in
                [`~PreTrainedTokenizerBase.__call__`]

        Returns:
            `List[str]`: The list of tokens.
        """
        raise NotImplementedError

    def encode(
        self,
        text: Union[TextInput, PreTokenizedInput, EncodedInput],
        text_pair: Optional[Union[TextInput, PreTokenizedInput, EncodedInput]] = None,
        add_special_tokens: bool = True,
        padding: Union[bool, str, PaddingStrategy] = False,
        truncation: Union[bool, str, TruncationStrategy] = None,
        max_length: Optional[int] = None,
        stride: int = 0,
        return_tensors: Optional[Union[str, TensorType]] = None,
        **kwargs,
    ) -> List[int]:
        """
        Converts a string to a sequence of ids (integer), using the tokenizer and vocabulary.

        Same as doing `self.convert_tokens_to_ids(self.tokenize(text))`.

        Args:
            text (`str`, `List[str]` or `List[int]`):
                The first sequence to be encoded. This can be a string, a list of strings (tokenized string using the
                `tokenize` method) or a list of integers (tokenized string ids using the `convert_tokens_to_ids`
                method).
            text_pair (`str`, `List[str]` or `List[int]`, *optional*):
                Optional second sequence to be encoded. This can be a string, a list of strings (tokenized string using
                the `tokenize` method) or a list of integers (tokenized string ids using the `convert_tokens_to_ids`
                method).
        """
        encoded_inputs = self.encode_plus(
            text,
            text_pair=text_pair,
            add_special_tokens=add_special_tokens,
            padding=padding,
            truncation=truncation,
            max_length=max_length,
            stride=stride,
            return_tensors=return_tensors,
            **kwargs,
        )

        return encoded_inputs["input_ids"]

    def num_special_tokens_to_add(self, pair: bool = False) -> int:
        r"""
        num_special_tokens_to_add method in the PreTrainedTokenizerBase class calculates the number of special tokens to be added.

        Args:
            self: An instance of the PreTrainedTokenizerBase class.
            pair (bool): A boolean flag indicating whether the tokens are paired. Defaults to False.

        Returns:
            int: The number of special tokens to be added based on the input parameters.

        Raises:
            NotImplementedError: If the method is called directly from the base class without being implemented in the derived class.
        """
        raise NotImplementedError

    def _get_padding_truncation_strategies(
        self, padding=False, truncation=None, max_length=None, pad_to_multiple_of=None, verbose=True, **kwargs
    ):
        """
        Find the correct padding/truncation strategy with backward compatibility for old arguments (truncation_strategy
        and pad_to_max_length) and behaviors.
        """
        old_truncation_strategy = kwargs.pop("truncation_strategy", "do_not_truncate")
        old_pad_to_max_length = kwargs.pop("pad_to_max_length", False)

        # Backward compatibility for previous behavior, maybe we should deprecate it:
        # If you only set max_length, it activates truncation for max_length
        if max_length is not None and padding is False and truncation is None:
            if verbose:
                if not self.deprecation_warnings.get("Truncation-not-explicitly-activated", False):
                    logger.warning(
                        "Truncation was not explicitly activated but `max_length` is provided a specific value, please"
                        " use `truncation=True` to explicitly truncate examples to max length. Defaulting to"
                        " 'longest_first' truncation strategy. If you encode pairs of sequences (GLUE-style) with the"
                        " tokenizer you can select this strategy more precisely by providing a specific strategy to"
                        " `truncation`."
                    )
                self.deprecation_warnings["Truncation-not-explicitly-activated"] = True
            truncation = "longest_first"

        # Get padding strategy
        if padding is False and old_pad_to_max_length:
            if verbose:
                warnings.warn(
                    "The `pad_to_max_length` argument is deprecated and will be removed in a future version, "
                    "use `padding=True` or `padding='longest'` to pad to the longest sequence in the batch, or "
                    "use `padding='max_length'` to pad to a max length. In this case, you can give a specific "
                    "length with `max_length` (e.g. `max_length=45`) or leave max_length to None to pad to the "
                    "maximal input size of the model (e.g. 512 for Bert).",
                    FutureWarning,
                )
            if max_length is None:
                padding_strategy = PaddingStrategy.LONGEST
            else:
                padding_strategy = PaddingStrategy.MAX_LENGTH
        elif padding is not False:
            if padding is True:
                if verbose:
                    if max_length is not None and (
                        truncation is None or truncation is False or truncation == "do_not_truncate"
                    ):
                        warnings.warn(
                            "`max_length` is ignored when `padding`=`True` and there is no truncation strategy. "
                            "To pad to max length, use `padding='max_length'`."
                        )
                    if old_pad_to_max_length is not False:
                        warnings.warn("Though `pad_to_max_length` = `True`, it is ignored because `padding`=`True`.")
                padding_strategy = PaddingStrategy.LONGEST  # Default to pad to the longest sequence in the batch
            elif not isinstance(padding, PaddingStrategy):
                padding_strategy = PaddingStrategy(padding)
            elif isinstance(padding, PaddingStrategy):
                padding_strategy = padding
        else:
            padding_strategy = PaddingStrategy.DO_NOT_PAD

        # Get truncation strategy
        if truncation is None and old_truncation_strategy != "do_not_truncate":
            if verbose:
                warnings.warn(
                    "The `truncation_strategy` argument is deprecated and will be removed in a future version, use"
                    " `truncation=True` to truncate examples to a max length. You can give a specific length with"
                    " `max_length` (e.g. `max_length=45`) or leave max_length to None to truncate to the maximal input"
                    " size of the model (e.g. 512 for Bert).  If you have pairs of inputs, you can give a specific"
                    " truncation strategy selected among `truncation='only_first'` (will only truncate the first"
                    " sentence in the pairs) `truncation='only_second'` (will only truncate the second sentence in the"
                    " pairs) or `truncation='longest_first'` (will iteratively remove tokens from the longest sentence"
                    " in the pairs).",
                    FutureWarning,
                )
            truncation_strategy = TruncationStrategy(old_truncation_strategy)
        elif truncation is not False and truncation is not None:
            if truncation is True:
                truncation_strategy = (
                    TruncationStrategy.LONGEST_FIRST
                )  # Default to truncate the longest sequences in pairs of inputs
            elif not isinstance(truncation, TruncationStrategy):
                truncation_strategy = TruncationStrategy(truncation)
            elif isinstance(truncation, TruncationStrategy):
                truncation_strategy = truncation
        else:
            truncation_strategy = TruncationStrategy.DO_NOT_TRUNCATE

        # Set max length if needed
        if max_length is None:
            if padding_strategy == PaddingStrategy.MAX_LENGTH:
                if self.model_max_length > LARGE_INTEGER:
                    if verbose:
                        if not self.deprecation_warnings.get("Asking-to-pad-to-max_length", False):
                            logger.warning(
                                "Asking to pad to max_length but no maximum length is provided and the model has no"
                                " predefined maximum length. Default to no padding."
                            )
                        self.deprecation_warnings["Asking-to-pad-to-max_length"] = True
                    padding_strategy = PaddingStrategy.DO_NOT_PAD
                else:
                    max_length = self.model_max_length

            if truncation_strategy != TruncationStrategy.DO_NOT_TRUNCATE:
                if self.model_max_length > LARGE_INTEGER:
                    if verbose:
                        if not self.deprecation_warnings.get("Asking-to-truncate-to-max_length", False):
                            logger.warning(
                                "Asking to truncate to max_length but no maximum length is provided and the model has"
                                " no predefined maximum length. Default to no truncation."
                            )
                        self.deprecation_warnings["Asking-to-truncate-to-max_length"] = True
                    truncation_strategy = TruncationStrategy.DO_NOT_TRUNCATE
                else:
                    max_length = self.model_max_length

        # Test if we have a padding token
        if padding_strategy != PaddingStrategy.DO_NOT_PAD and (self.pad_token is None or self.pad_token_id < 0):
            raise ValueError(
                "Asking to pad but the tokenizer does not have a padding token. "
                "Please select a token to use as `pad_token` `(tokenizer.pad_token = tokenizer.eos_token e.g.)` "
                "or add a new pad token via `tokenizer.add_special_tokens({'pad_token': '[PAD]'})`."
            )

        # Check that we will truncate to a multiple of pad_to_multiple_of if both are provided
        if (
            truncation_strategy != TruncationStrategy.DO_NOT_TRUNCATE
            and padding_strategy != PaddingStrategy.DO_NOT_PAD
            and pad_to_multiple_of is not None
            and max_length is not None
            and (max_length % pad_to_multiple_of != 0)
        ):
            raise ValueError(
                "Truncation and padding are both activated but "
                f"truncation length ({max_length}) is not a multiple of pad_to_multiple_of ({pad_to_multiple_of})."
            )

        return padding_strategy, truncation_strategy, max_length, kwargs

    def __call__(
        self,
        text: Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]] = None,
        text_pair: Optional[Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]]] = None,
        text_target: Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]] = None,
        text_pair_target: Optional[
            Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]]
        ] = None,
        add_special_tokens: bool = True,
        padding: Union[bool, str, PaddingStrategy] = False,
        truncation: Union[bool, str, TruncationStrategy] = None,
        max_length: Optional[int] = None,
        stride: int = 0,
        is_split_into_words: bool = False,
        pad_to_multiple_of: Optional[int] = None,
        return_tensors: Optional[Union[str, TensorType]] = None,
        return_token_type_ids: Optional[bool] = None,
        return_attention_mask: Optional[bool] = None,
        return_overflowing_tokens: bool = False,
        return_special_tokens_mask: bool = False,
        return_offsets_mapping: bool = False,
        return_length: bool = False,
        verbose: bool = True,
        **kwargs,
    ) -> BatchEncoding:
        """
        Main method to tokenize and prepare for the model one or several sequence(s) or one or several pair(s) of
        sequences.

        Args:
            text (`str`, `List[str]`, `List[List[str]]`, *optional*):
                The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings
                (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
                `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
            text_pair (`str`, `List[str]`, `List[List[str]]`, *optional*):
                The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings
                (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
                `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
            text_target (`str`, `List[str]`, `List[List[str]]`, *optional*):
                The sequence or batch of sequences to be encoded as target texts. Each sequence can be a string or a
                list of strings (pretokenized string). If the sequences are provided as list of strings (pretokenized),
                you must set `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
            text_pair_target (`str`, `List[str]`, `List[List[str]]`, *optional*):
                The sequence or batch of sequences to be encoded as target texts. Each sequence can be a string or a
                list of strings (pretokenized string). If the sequences are provided as list of strings (pretokenized),
                you must set `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
        """
        # To avoid duplicating
        all_kwargs = {
            "add_special_tokens": add_special_tokens,
            "padding": padding,
            "truncation": truncation,
            "max_length": max_length,
            "stride": stride,
            "is_split_into_words": is_split_into_words,
            "pad_to_multiple_of": pad_to_multiple_of,
            "return_tensors": return_tensors,
            "return_token_type_ids": return_token_type_ids,
            "return_attention_mask": return_attention_mask,
            "return_overflowing_tokens": return_overflowing_tokens,
            "return_special_tokens_mask": return_special_tokens_mask,
            "return_offsets_mapping": return_offsets_mapping,
            "return_length": return_length,
            "verbose": verbose,
        }
        all_kwargs.update(kwargs)
        if text is None and text_target is None:
            raise ValueError("You need to specify either `text` or `text_target`.")
        if text is not None:
            # for mindspore.dataset
            if isinstance(text, np.ndarray):
                text = str(text)
                if isinstance(text_pair, np.ndarray):
                    text_pair = str(text_pair)
                elif isinstance(text_pair, list):
                    text_pair = [str(t) for t in text_pair]
            # The context manager will send the inputs as normal texts and not text_target, but we shouldn't change the
            # input mode in this case.
            if not self._in_target_context_manager:
                self._switch_to_input_mode()
            encodings = self._call_one(text=text, text_pair=text_pair, **all_kwargs)
        if text_target is not None:
            self._switch_to_target_mode()
            target_encodings = self._call_one(text=text_target, text_pair=text_pair_target, **all_kwargs)
        # Leave back tokenizer in input mode
        self._switch_to_input_mode()

        if text_target is None:
            return encodings
        if text is None:
            return target_encodings
        encodings["labels"] = target_encodings["input_ids"]
        return encodings

    def _call_one(
        self,
        text: Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]],
        text_pair: Optional[Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]]] = None,
        add_special_tokens: bool = True,
        padding: Union[bool, str, PaddingStrategy] = False,
        truncation: Union[bool, str, TruncationStrategy] = None,
        max_length: Optional[int] = None,
        stride: int = 0,
        is_split_into_words: bool = False,
        pad_to_multiple_of: Optional[int] = None,
        return_tensors: Optional[Union[str, TensorType]] = None,
        return_token_type_ids: Optional[bool] = None,
        return_attention_mask: Optional[bool] = None,
        return_overflowing_tokens: bool = False,
        return_special_tokens_mask: bool = False,
        return_offsets_mapping: bool = False,
        return_length: bool = False,
        verbose: bool = True,
        **kwargs,
    ) -> BatchEncoding:
        r"""
        This method '_call_one' in the class 'PreTrainedTokenizerBase' takes 18 parameters:

        Args:
            self: The instance of the class.
            text: Input text data to be tokenized. It can be a single example (str), a list of single examples (List[str]),
                or a list of pretokenized examples (List[List[str]]).
            text_pair: Optional input text data to be tokenized when processing pairs of text.
                It follows the same format as 'text'.
            add_special_tokens: A boolean flag indicating whether special tokens should be added during tokenization.
            padding: Specifies the padding strategy to use during tokenization.
                It can be a boolean value, a string, or a PaddingStrategy enum.
            truncation: Specifies the truncation strategy to use during tokenization.
                It can be a boolean value, a string, or a TruncationStrategy enum.
            max_length: The maximum length of the tokenized sequences.
            stride: Integer specifying the stride when overflowing tokens.
            is_split_into_words: A boolean flag indicating if the input text is already split into words.
            pad_to_multiple_of: Optional integer specifying a multiple to pad the sequence length to.
            return_tensors: Specifies the type of tensors to return (e.g., 'pt' for PyTorch tensors).
            return_token_type_ids: A boolean flag indicating whether token type IDs should be returned.
            return_attention_mask: A boolean flag indicating whether attention masks should be returned.
            return_overflowing_tokens: A boolean flag indicating whether overflowing tokens should be returned.
            return_special_tokens_mask: A boolean flag indicating whether special tokens masks should be returned.
            return_offsets_mapping: A boolean flag indicating whether offsets mapping should be returned.
            return_length: A boolean flag indicating whether tokenized sequence lengths should be returned.
            verbose: A boolean flag indicating whether to output verbose information during tokenization.

        Returns:
            A BatchEncoding object containing the tokenized input data with additional information depending on the specified return flags.

        Raises:
            ValueError: If the input text does not conform to the expected types or structures.
            TypeError: If 'text_pair' is a string when tokenizing batches of text.
            ValueError: If the batch lengths of 'text' and 'text_pair' do not match.
        """
        # Input type checking for clearer error
        def _is_valid_text_input(t):
            if isinstance(t, str):
                # Strings are fine
                return True
            if isinstance(t, (list, tuple)):
                # List are fine as long as they are...
                if len(t) == 0:
                    # ... empty
                    return True
                if isinstance(t[0], str):
                    # ... list of strings
                    return True
                if isinstance(t[0], (list, tuple)):
                    # ... list with an empty list or with a list of strings
                    return len(t[0]) == 0 or isinstance(t[0][0], str)
                return False
            return False

        if not _is_valid_text_input(text):
            raise ValueError(
                "text input must of type `str` (single example), `List[str]` (batch or single pretokenized example) "
                "or `List[List[str]]` (batch of pretokenized examples)."
            )

        if text_pair is not None and not _is_valid_text_input(text_pair):
            raise ValueError(
                "text input must of type `str` (single example), `List[str]` (batch or single pretokenized example) "
                "or `List[List[str]]` (batch of pretokenized examples)."
            )

        if is_split_into_words:
            is_batched = isinstance(text, (list, tuple)) and text and isinstance(text[0], (list, tuple))
        else:
            is_batched = isinstance(text, (list, tuple))

        if is_batched:
            if isinstance(text_pair, str):
                raise TypeError(
                    "when tokenizing batches of text, `text_pair` must be a list or tuple with the same length as"
                    " `text`."
                )
            if text_pair is not None and len(text) != len(text_pair):
                raise ValueError(
                    f"batch length of `text`: {len(text)} does not match batch length of `text_pair`:"
                    f" {len(text_pair)}."
                )
            batch_text_or_text_pairs = list(zip(text, text_pair)) if text_pair is not None else text
            return self.batch_encode_plus(
                batch_text_or_text_pairs=batch_text_or_text_pairs,
                add_special_tokens=add_special_tokens,
                padding=padding,
                truncation=truncation,
                max_length=max_length,
                stride=stride,
                is_split_into_words=is_split_into_words,
                pad_to_multiple_of=pad_to_multiple_of,
                return_tensors=return_tensors,
                return_token_type_ids=return_token_type_ids,
                return_attention_mask=return_attention_mask,
                return_overflowing_tokens=return_overflowing_tokens,
                return_special_tokens_mask=return_special_tokens_mask,
                return_offsets_mapping=return_offsets_mapping,
                return_length=return_length,
                verbose=verbose,
                **kwargs,
            )
        return self.encode_plus(
            text=text,
            text_pair=text_pair,
            add_special_tokens=add_special_tokens,
            padding=padding,
            truncation=truncation,
            max_length=max_length,
            stride=stride,
            is_split_into_words=is_split_into_words,
            pad_to_multiple_of=pad_to_multiple_of,
            return_tensors=return_tensors,
            return_token_type_ids=return_token_type_ids,
            return_attention_mask=return_attention_mask,
            return_overflowing_tokens=return_overflowing_tokens,
            return_special_tokens_mask=return_special_tokens_mask,
            return_offsets_mapping=return_offsets_mapping,
            return_length=return_length,
            verbose=verbose,
            **kwargs,
        )

    def encode_plus(
        self,
        text: Union[TextInput, PreTokenizedInput, EncodedInput],
        text_pair: Optional[Union[TextInput, PreTokenizedInput, EncodedInput]] = None,
        add_special_tokens: bool = True,
        padding: Union[bool, str, PaddingStrategy] = False,
        truncation: Union[bool, str, TruncationStrategy] = None,
        max_length: Optional[int] = None,
        stride: int = 0,
        is_split_into_words: bool = False,
        pad_to_multiple_of: Optional[int] = None,
        return_tensors: Optional[Union[str, TensorType]] = None,
        return_token_type_ids: Optional[bool] = None,
        return_attention_mask: Optional[bool] = None,
        return_overflowing_tokens: bool = False,
        return_special_tokens_mask: bool = False,
        return_offsets_mapping: bool = False,
        return_length: bool = False,
        verbose: bool = True,
        **kwargs,
    ) -> BatchEncoding:
        """
        Tokenize and prepare for the model a sequence or a pair of sequences.

        <Tip warning={true}>

        This method is deprecated, `__call__` should be used instead.

        </Tip>

        Args:
            text (`str`, `List[str]` or `List[int]` (the latter only for not-fast tokenizers)):
                The first sequence to be encoded. This can be a string, a list of strings (tokenized string using the
                `tokenize` method) or a list of integers (tokenized string ids using the `convert_tokens_to_ids`
                method).
            text_pair (`str`, `List[str]` or `List[int]`, *optional*):
                Optional second sequence to be encoded. This can be a string, a list of strings (tokenized string using
                the `tokenize` method) or a list of integers (tokenized string ids using the `convert_tokens_to_ids`
                method).
        """
        # Backward compatibility for 'truncation_strategy', 'pad_to_max_length'
        padding_strategy, truncation_strategy, max_length, kwargs = self._get_padding_truncation_strategies(
            padding=padding,
            truncation=truncation,
            max_length=max_length,
            pad_to_multiple_of=pad_to_multiple_of,
            verbose=verbose,
            **kwargs,
        )

        return self._encode_plus(
            text=text,
            text_pair=text_pair,
            add_special_tokens=add_special_tokens,
            padding_strategy=padding_strategy,
            truncation_strategy=truncation_strategy,
            max_length=max_length,
            stride=stride,
            is_split_into_words=is_split_into_words,
            pad_to_multiple_of=pad_to_multiple_of,
            return_tensors=return_tensors,
            return_token_type_ids=return_token_type_ids,
            return_attention_mask=return_attention_mask,
            return_overflowing_tokens=return_overflowing_tokens,
            return_special_tokens_mask=return_special_tokens_mask,
            return_offsets_mapping=return_offsets_mapping,
            return_length=return_length,
            verbose=verbose,
            **kwargs,
        )

    def _encode_plus(
        self,
        text: Union[TextInput, PreTokenizedInput, EncodedInput],
        text_pair: Optional[Union[TextInput, PreTokenizedInput, EncodedInput]] = None,
        add_special_tokens: bool = True,
        padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
        truncation_strategy: TruncationStrategy = TruncationStrategy.DO_NOT_TRUNCATE,
        max_length: Optional[int] = None,
        stride: int = 0,
        is_split_into_words: bool = False,
        pad_to_multiple_of: Optional[int] = None,
        return_tensors: Optional[Union[str, TensorType]] = None,
        return_token_type_ids: Optional[bool] = None,
        return_attention_mask: Optional[bool] = None,
        return_overflowing_tokens: bool = False,
        return_special_tokens_mask: bool = False,
        return_offsets_mapping: bool = False,
        return_length: bool = False,
        verbose: bool = True,
        **kwargs,
    ) -> BatchEncoding:
        r"""
        Method _encode_plus in the class PreTrainedTokenizerBase.

        Args:
            self: The instance of the class.
            text: Input text to encode. Can be of type TextInput, PreTokenizedInput, or EncodedInput.
            text_pair: Optional second input text to encode. Can be of type TextInput, PreTokenizedInput, or EncodedInput.
            add_special_tokens: A boolean indicating whether to add special tokens. Default is True.
            padding_strategy: The strategy for padding tokens. Default is PaddingStrategy.DO_NOT_PAD.
            truncation_strategy: The strategy for truncating tokens. Default is TruncationStrategy.DO_NOT_TRUNCATE.
            max_length: The maximum length of the returned list of tensors.
            stride: An integer indicating the tokenization stride. Default is 0.
            is_split_into_words: A boolean indicating if the input text is already split into words.
            pad_to_multiple_of: The padding length will be a multiple of this value.
            return_tensors: Specify the type of the returned tensors. Can be a string or TensorType.
            return_token_type_ids: A boolean indicating whether to return token type IDs.
            return_attention_mask: A boolean indicating whether to return attention masks.
            return_overflowing_tokens: A boolean indicating whether to return overflowing tokens.
            return_special_tokens_mask: A boolean indicating whether to return special tokens masks.
            return_offsets_mapping: A boolean indicating whether to return token offset mappings.
            return_length: A boolean indicating whether to return the length of input sequences.
            verbose: A boolean indicating whether to print verbose information.

        Returns:
            BatchEncoding: A dictionary containing the encoded inputs ready for model processing.

        Raises:
            NotImplementedError: If the method is called and not implemented.
        """
        raise NotImplementedError

    def batch_encode_plus(
        self,
        batch_text_or_text_pairs: Union[
            List[TextInput],
            List[TextInputPair],
            List[PreTokenizedInput],
            List[PreTokenizedInputPair],
            List[EncodedInput],
            List[EncodedInputPair],
        ],
        add_special_tokens: bool = True,
        padding: Union[bool, str, PaddingStrategy] = False,
        truncation: Union[bool, str, TruncationStrategy] = None,
        max_length: Optional[int] = None,
        stride: int = 0,
        is_split_into_words: bool = False,
        pad_to_multiple_of: Optional[int] = None,
        return_tensors: Optional[Union[str, TensorType]] = None,
        return_token_type_ids: Optional[bool] = None,
        return_attention_mask: Optional[bool] = None,
        return_overflowing_tokens: bool = False,
        return_special_tokens_mask: bool = False,
        return_offsets_mapping: bool = False,
        return_length: bool = False,
        verbose: bool = True,
        **kwargs,
    ) -> BatchEncoding:
        """
        Tokenize and prepare for the model a list of sequences or a list of pairs of sequences.

        <Tip warning={true}>

        This method is deprecated, `__call__` should be used instead.

        </Tip>

        Args:
            batch_text_or_text_pairs (`List[str]`, `List[Tuple[str, str]]`, `List[List[str]]`, `List[Tuple[List[str], List[str]]]`, and for not-fast tokenizers,
            also `List[List[int]]`, `List[Tuple[List[int], List[int]]]`):
                Batch of sequences or pair of sequences to be encoded. This can be a list of
                string/string-sequences/int-sequences or a list of pair of string/string-sequences/int-sequence (see
                details in `encode_plus`).
        """
        # Backward compatibility for 'truncation_strategy', 'pad_to_max_length'
        padding_strategy, truncation_strategy, max_length, kwargs = self._get_padding_truncation_strategies(
            padding=padding,
            truncation=truncation,
            max_length=max_length,
            pad_to_multiple_of=pad_to_multiple_of,
            verbose=verbose,
            **kwargs,
        )

        return self._batch_encode_plus(
            batch_text_or_text_pairs=batch_text_or_text_pairs,
            add_special_tokens=add_special_tokens,
            padding_strategy=padding_strategy,
            truncation_strategy=truncation_strategy,
            max_length=max_length,
            stride=stride,
            is_split_into_words=is_split_into_words,
            pad_to_multiple_of=pad_to_multiple_of,
            return_tensors=return_tensors,
            return_token_type_ids=return_token_type_ids,
            return_attention_mask=return_attention_mask,
            return_overflowing_tokens=return_overflowing_tokens,
            return_special_tokens_mask=return_special_tokens_mask,
            return_offsets_mapping=return_offsets_mapping,
            return_length=return_length,
            verbose=verbose,
            **kwargs,
        )

    def _batch_encode_plus(
        self,
        batch_text_or_text_pairs: Union[
            List[TextInput],
            List[TextInputPair],
            List[PreTokenizedInput],
            List[PreTokenizedInputPair],
            List[EncodedInput],
            List[EncodedInputPair],
        ],
        add_special_tokens: bool = True,
        padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
        truncation_strategy: TruncationStrategy = TruncationStrategy.DO_NOT_TRUNCATE,
        max_length: Optional[int] = None,
        stride: int = 0,
        is_split_into_words: bool = False,
        pad_to_multiple_of: Optional[int] = None,
        return_tensors: Optional[Union[str, TensorType]] = None,
        return_token_type_ids: Optional[bool] = None,
        return_attention_mask: Optional[bool] = None,
        return_overflowing_tokens: bool = False,
        return_special_tokens_mask: bool = False,
        return_offsets_mapping: bool = False,
        return_length: bool = False,
        verbose: bool = True,
        **kwargs,
    ) -> BatchEncoding:
        r"""
        Batch encode a batch of text or text pairs using various encoding strategies.

        Args:
            self (PreTrainedTokenizerBase): An instance of the PreTrainedTokenizerBase class.
            batch_text_or_text_pairs (Union[List[TextInput], List[TextInputPair], List[PreTokenizedInput], List[PreTokenizedInputPair], List[EncodedInput], List[EncodedInputPair]]):
                A list of text or text pairs to be encoded. The input can be in various formats, such as raw text, pre-tokenized text, or encoded input.
            add_special_tokens (bool, optional): Whether to add special tokens to the encoded sequences. Defaults to True.
            padding_strategy (PaddingStrategy, optional): The strategy to use for padding sequences. Defaults to PaddingStrategy.DO_NOT_PAD.
            truncation_strategy (TruncationStrategy, optional): The strategy to use for truncating sequences. Defaults to TruncationStrategy.DO_NOT_TRUNCATE.
            max_length (int, optional): The maximum length of the encoded sequences. If set to None, the sequences are not truncated. Defaults to None.
            stride (int, optional): The stride to use when overflowing tokens. Defaults to 0.
            is_split_into_words (bool, optional): Whether the input is already split into words. Defaults to False.
            pad_to_multiple_of (int, optional): The padding length will be a multiple of this value. Defaults to None.
            return_tensors (Union[str, TensorType], optional): The type of tensor to return. Defaults to None.
            return_token_type_ids (bool, optional): Whether to return token type IDs. Defaults to None.
            return_attention_mask (bool, optional): Whether to return attention masks. Defaults to None.
            return_overflowing_tokens (bool, optional): Whether to return overflowing tokens. Defaults to False.
            return_special_tokens_mask (bool, optional): Whether to return a special tokens mask. Defaults to False.
            return_offsets_mapping (bool, optional): Whether to return the offsets mapping. Defaults to False.
            return_length (bool, optional): Whether to return the length of the encoded sequences. Defaults to False.
            verbose (bool, optional): Whether to print information during encoding. Defaults to True.
            **kwargs: Additional keyword arguments for specific tokenizer implementations.

        Returns:
            BatchEncoding: An object containing the batch of encoded sequences, along with additional information such as attention masks, token type IDs, and length.

        Raises:
            NotImplementedError: If the method is not implemented by a subclass.

        """
        raise NotImplementedError

    def pad(
        self,
        encoded_inputs: Union[
            BatchEncoding,
            List[BatchEncoding],
            Dict[str, EncodedInput],
            Dict[str, List[EncodedInput]],
            List[Dict[str, EncodedInput]],
        ],
        padding: Union[bool, str, PaddingStrategy] = True,
        max_length: Optional[int] = None,
        pad_to_multiple_of: Optional[int] = None,
        return_attention_mask: Optional[bool] = None,
        return_tensors: Optional[Union[str, TensorType]] = None,
        verbose: bool = True,
    ) -> BatchEncoding:
        """
        Pad a single encoded input or a batch of encoded inputs up to predefined length or to the max sequence length
        in the batch.

        Padding side (left/right) padding token ids are defined at the tokenizer level (with `self.padding_side`,
        `self.pad_token_id` and `self.pad_token_type_id`).

        Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the
        text followed by a call to the `pad` method to get a padded encoding.

        <Tip>

        If the `encoded_inputs` passed are dictionary of numpy arrays, PyTorch tensors or TensorFlow tensors, the
        result will use the same type unless you provide a different tensor type with `return_tensors`. In the case of
        PyTorch tensors, you will lose the specific device of your tensors however.

        </Tip>

        Args:
            encoded_inputs ([`BatchEncoding`], list of [`BatchEncoding`], `Dict[str, List[int]]`, `Dict[str, List[List[int]]` or `List[Dict[str, List[int]]]`):
                Tokenized inputs. Can represent one input ([`BatchEncoding`] or `Dict[str, List[int]]`) or a batch of
                tokenized inputs (list of [`BatchEncoding`], *Dict[str, List[List[int]]]* or *List[Dict[str,
                List[int]]]*) so you can use this method during preprocessing as well as in a PyTorch Dataloader
                collate function.

                Instead of `List[int]` you can have tensors (numpy arrays, PyTorch tensors or TensorFlow tensors), see
                the note above for the return type.
            padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `True`):
                 Select a strategy to pad the returned sequences (according to the model's padding side and padding
                 index) among:

                - `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single
                  sequence if provided).
                - `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum
                  acceptable input length for the model if that argument is not provided.
                - `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different
                  lengths).
            max_length (`int`, *optional*):
                Maximum length of the returned list and optionally padding length (see above).
            pad_to_multiple_of (`int`, *optional*):
                If set will pad the sequence to a multiple of the provided value.

                This is especially useful to enable the use of Tensor Cores on NVIDIA hardware with compute capability
                `>= 7.5` (Volta).
            return_attention_mask (`bool`, *optional*):
                Whether to return the attention mask. If left to the default, will return the attention mask according
                to the specific tokenizer's default, defined by the `return_outputs` attribute.

                [What are attention masks?](../glossary#attention-mask)
            return_tensors (`str` or [`~utils.TensorType`], *optional*):
                If set, will return tensors instead of list of python integers. Acceptable values are:

                - `'tf'`: Return TensorFlow `tf.constant` objects.
                - `'pt'`: Return PyTorch `mindspore.Tensor` objects.
                - `'np'`: Return Numpy `np.ndarray` objects.
            verbose (`bool`, *optional*, defaults to `True`):
                Whether or not to print more information and warnings.
        """
        if self.__class__.__name__.endswith("Fast"):
            if not self.deprecation_warnings.get("Asking-to-pad-a-fast-tokenizer", False):
                logger.warning_advice(
                    f"You're using a {self.__class__.__name__} tokenizer. Please note that with a fast tokenizer,"
                    " using the `__call__` method is faster than using a method to encode the text followed by a call"
                    " to the `pad` method to get a padded encoding."
                )
                self.deprecation_warnings["Asking-to-pad-a-fast-tokenizer"] = True

        # If we have a list of dicts, let's convert it in a dict of lists
        # We do this to allow using this method as a collate_fn function in PyTorch Dataloader
        if isinstance(encoded_inputs, (list, tuple)) and isinstance(encoded_inputs[0], Mapping):
            encoded_inputs = {key: [example[key] for example in encoded_inputs] for key in encoded_inputs[0].keys()}

        # The model's main input name, usually `input_ids`, has be passed for padding
        if self.model_input_names[0] not in encoded_inputs:
            raise ValueError(
                "You should supply an encoding or a list of encodings to this method "
                f"that includes {self.model_input_names[0]}, but you provided {list(encoded_inputs.keys())}"
            )

        required_input = encoded_inputs[self.model_input_names[0]]

        if required_input is None or (isinstance(required_input, Sized) and len(required_input) == 0):
            if return_attention_mask:
                encoded_inputs["attention_mask"] = []
            return encoded_inputs

        # If we have PyTorch/TF/NumPy tensors/arrays as inputs, we cast them as python objects
        # and rebuild them afterwards if no return_tensors is specified
        # Note that we lose the specific device the tensor may be on for PyTorch

        first_element = required_input[0]
        if isinstance(first_element, (list, tuple)):
            # first_element might be an empty list/tuple in some edge cases so we grab the first non empty element.
            for item in required_input:
                if len(item) != 0:
                    first_element = item[0]
                    break
        # At this state, if `first_element` is still a list/tuple, it's an empty one so there is nothing to do.
        if not isinstance(first_element, (int, list, tuple)):
            if isinstance(first_element, mindspore.Tensor):
                return_tensors = "ms" if return_tensors is None else return_tensors
            elif isinstance(first_element, np.ndarray):
                return_tensors = "np" if return_tensors is None else return_tensors
            else:
                raise ValueError(
                    f"type of {first_element} unknown: {type(first_element)}. "
                    "Should be one of a python, numpy, pytorch or tensorflow object."
                )

            for key, value in encoded_inputs.items():
                encoded_inputs[key] = to_py_obj(value)

        # Convert padding_strategy in PaddingStrategy
        padding_strategy, _, max_length, _ = self._get_padding_truncation_strategies(
            padding=padding, max_length=max_length, verbose=verbose
        )

        required_input = encoded_inputs[self.model_input_names[0]]
        if required_input and not isinstance(required_input[0], (list, tuple)):
            encoded_inputs = self._pad(
                encoded_inputs,
                max_length=max_length,
                padding_strategy=padding_strategy,
                pad_to_multiple_of=pad_to_multiple_of,
                return_attention_mask=return_attention_mask,
            )
            return BatchEncoding(encoded_inputs, tensor_type=return_tensors)

        batch_size = len(required_input)
        assert all(
            len(v) == batch_size for v in encoded_inputs.values()
        ), "Some items in the output dictionary have a different batch size than others."

        if padding_strategy == PaddingStrategy.LONGEST:
            max_length = max(len(inputs) for inputs in required_input)
            padding_strategy = PaddingStrategy.MAX_LENGTH

        batch_outputs = {}
        for i in range(batch_size):
            inputs = {k: v[i] for k, v in encoded_inputs.items()}
            outputs = self._pad(
                inputs,
                max_length=max_length,
                padding_strategy=padding_strategy,
                pad_to_multiple_of=pad_to_multiple_of,
                return_attention_mask=return_attention_mask,
            )

            for key, value in outputs.items():
                if key not in batch_outputs:
                    batch_outputs[key] = []
                batch_outputs[key].append(value)

        return BatchEncoding(batch_outputs, tensor_type=return_tensors)

    def create_token_type_ids_from_sequences(
        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
    ) -> List[int]:
        """
        Create the token type IDs corresponding to the sequences passed. [What are token type
        IDs?](../glossary#token-type-ids)

        Should be overridden in a subclass if the model has a special way of building those.

        Args:
            token_ids_0 (`List[int]`): The first tokenized sequence.
            token_ids_1 (`List[int]`, *optional*): The second tokenized sequence.

        Returns:
            `List[int]`: The token type ids.
        """
        if token_ids_1 is None:
            return len(token_ids_0) * [0]
        return [0] * len(token_ids_0) + [1] * len(token_ids_1)

    def build_inputs_with_special_tokens(
        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
    ) -> List[int]:
        """
        Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
        adding special tokens.

        This implementation does not add special tokens and this method should be overridden in a subclass.

        Args:
            token_ids_0 (`List[int]`): The first tokenized sequence.
            token_ids_1 (`List[int]`, *optional*): The second tokenized sequence.

        Returns:
            `List[int]`: The model input with special tokens.
        """
        if token_ids_1 is None:
            return token_ids_0
        return token_ids_0 + token_ids_1

    def prepare_for_model(
        self,
        ids: List[int],
        pair_ids: Optional[List[int]] = None,
        add_special_tokens: bool = True,
        padding: Union[bool, str, PaddingStrategy] = False,
        truncation: Union[bool, str, TruncationStrategy] = None,
        max_length: Optional[int] = None,
        stride: int = 0,
        pad_to_multiple_of: Optional[int] = None,
        return_tensors: Optional[Union[str, TensorType]] = None,
        return_token_type_ids: Optional[bool] = None,
        return_attention_mask: Optional[bool] = None,
        return_overflowing_tokens: bool = False,
        return_special_tokens_mask: bool = False,
        return_offsets_mapping: bool = False,
        return_length: bool = False,
        verbose: bool = True,
        prepend_batch_axis: bool = False,
        **kwargs,
    ) -> BatchEncoding:
        """
        Prepares a sequence of input id, or a pair of sequences of inputs ids so that it can be used by the model. It
        adds special tokens, truncates sequences if overflowing while taking into account the special tokens and
        manages a moving window (with user defined stride) for overflowing tokens. Please Note, for *pair_ids*
        different than `None` and *truncation_strategy = longest_first* or `True`, it is not possible to return
        overflowing tokens. Such a combination of arguments will raise an error.

        Args:
            ids (`List[int]`):
                Tokenized input ids of the first sequence. Can be obtained from a string by chaining the `tokenize` and
                `convert_tokens_to_ids` methods.
            pair_ids (`List[int]`, *optional*):
                Tokenized input ids of the second sequence. Can be obtained from a string by chaining the `tokenize`
                and `convert_tokens_to_ids` methods.
        """
        # Backward compatibility for 'truncation_strategy', 'pad_to_max_length'
        padding_strategy, truncation_strategy, max_length, kwargs = self._get_padding_truncation_strategies(
            padding=padding,
            truncation=truncation,
            max_length=max_length,
            pad_to_multiple_of=pad_to_multiple_of,
            verbose=verbose,
            **kwargs,
        )

        pair = bool(pair_ids is not None)
        len_ids = len(ids)
        len_pair_ids = len(pair_ids) if pair else 0

        if return_token_type_ids and not add_special_tokens:
            raise ValueError(
                "Asking to return token_type_ids while setting add_special_tokens to False "
                "results in an undefined behavior. Please set add_special_tokens to True or "
                "set return_token_type_ids to None."
            )

        if (
            return_overflowing_tokens
            and truncation_strategy == TruncationStrategy.LONGEST_FIRST
            and pair_ids is not None
        ):
            raise ValueError(
                "Not possible to return overflowing tokens for pair of sequences with the "
                "`longest_first`. Please select another truncation strategy than `longest_first`, "
                "for instance `only_second` or `only_first`."
            )

        # Load from model defaults
        if return_token_type_ids is None:
            return_token_type_ids = "token_type_ids" in self.model_input_names
        if return_attention_mask is None:
            return_attention_mask = "attention_mask" in self.model_input_names

        encoded_inputs = {}

        # Compute the total size of the returned encodings
        total_len = len_ids + len_pair_ids + (self.num_special_tokens_to_add(pair=pair) if add_special_tokens else 0)

        # Truncation: Handle max sequence length
        overflowing_tokens = []
        if truncation_strategy != TruncationStrategy.DO_NOT_TRUNCATE and max_length and total_len > max_length:
            ids, pair_ids, overflowing_tokens = self.truncate_sequences(
                ids,
                pair_ids=pair_ids,
                num_tokens_to_remove=total_len - max_length,
                truncation_strategy=truncation_strategy,
                stride=stride,
            )

        if return_overflowing_tokens:
            encoded_inputs["overflowing_tokens"] = overflowing_tokens
            encoded_inputs["num_truncated_tokens"] = total_len - max_length

        # Add special tokens
        if add_special_tokens:
            sequence = self.build_inputs_with_special_tokens(ids, pair_ids)
            token_type_ids = self.create_token_type_ids_from_sequences(ids, pair_ids)
        else:
            sequence = ids + pair_ids if pair else ids
            token_type_ids = [0] * len(ids) + ([0] * len(pair_ids) if pair else [])

        # Build output dictionary
        encoded_inputs["input_ids"] = sequence
        if return_token_type_ids:
            encoded_inputs["token_type_ids"] = token_type_ids
        if return_special_tokens_mask:
            if add_special_tokens:
                encoded_inputs["special_tokens_mask"] = self.get_special_tokens_mask(ids, pair_ids)
            else:
                encoded_inputs["special_tokens_mask"] = [0] * len(sequence)

        # Check lengths
        self._eventual_warn_about_too_long_sequence(encoded_inputs["input_ids"], max_length, verbose)

        # Padding
        if padding_strategy != PaddingStrategy.DO_NOT_PAD or return_attention_mask:
            encoded_inputs = self.pad(
                encoded_inputs,
                max_length=max_length,
                padding=padding_strategy.value,
                pad_to_multiple_of=pad_to_multiple_of,
                return_attention_mask=return_attention_mask,
            )

        if return_length:
            encoded_inputs["length"] = len(encoded_inputs["input_ids"])

        batch_outputs = BatchEncoding(
            encoded_inputs, tensor_type=return_tensors, prepend_batch_axis=prepend_batch_axis
        )

        return batch_outputs

    def truncate_sequences(
        self,
        ids: List[int],
        pair_ids: Optional[List[int]] = None,
        num_tokens_to_remove: int = 0,
        truncation_strategy: Union[str, TruncationStrategy] = "longest_first",
        stride: int = 0,
    ) -> Tuple[List[int], List[int], List[int]]:
        """
        Truncates a sequence pair in-place following the strategy.

        Args:
            ids (`List[int]`):
                Tokenized input ids of the first sequence. Can be obtained from a string by chaining the `tokenize` and
                `convert_tokens_to_ids` methods.
            pair_ids (`List[int]`, *optional*):
                Tokenized input ids of the second sequence. Can be obtained from a string by chaining the `tokenize`
                and `convert_tokens_to_ids` methods.
            num_tokens_to_remove (`int`, *optional*, defaults to 0):
                Number of tokens to remove using the truncation strategy.
            truncation_strategy (`str` or [`~tokenization_utils_base.TruncationStrategy`], *optional*, defaults to `False`):
                The strategy to follow for truncation. Can be:

                - `'longest_first'`: Truncate to a maximum length specified with the argument `max_length` or to the
                  maximum acceptable input length for the model if that argument is not provided. This will truncate
                  token by token, removing a token from the longest sequence in the pair if a pair of sequences (or a
                  batch of pairs) is provided.
                - `'only_first'`: Truncate to a maximum length specified with the argument `max_length` or to the
                  maximum acceptable input length for the model if that argument is not provided. This will only
                  truncate the first sequence of a pair if a pair of sequences (or a batch of pairs) is provided.
                - `'only_second'`: Truncate to a maximum length specified with the argument `max_length` or to the
                  maximum acceptable input length for the model if that argument is not provided. This will only
                  truncate the second sequence of a pair if a pair of sequences (or a batch of pairs) is provided.
                - `'do_not_truncate'` (default): No truncation (i.e., can output batch with sequence lengths greater
                  than the model maximum admissible input size).
            stride (`int`, *optional*, defaults to 0):
                If set to a positive number, the overflowing tokens returned will contain some tokens from the main
                sequence returned. The value of this argument defines the number of additional tokens.

        Returns:
            `Tuple[List[int], List[int], List[int]]`: The truncated `ids`, the truncated `pair_ids` and the list of
            overflowing tokens. Note: The *longest_first* strategy returns empty list of overflowing tokens if a pair
            of sequences (or a batch of pairs) is provided.
        """
        if num_tokens_to_remove <= 0:
            return ids, pair_ids, []

        if not isinstance(truncation_strategy, TruncationStrategy):
            truncation_strategy = TruncationStrategy(truncation_strategy)

        overflowing_tokens = []
        if truncation_strategy == TruncationStrategy.ONLY_FIRST or (
            truncation_strategy == TruncationStrategy.LONGEST_FIRST and pair_ids is None
        ):
            if len(ids) > num_tokens_to_remove:
                window_len = min(len(ids), stride + num_tokens_to_remove)
                if self.truncation_side == "left":
                    overflowing_tokens = ids[:window_len]
                    ids = ids[num_tokens_to_remove:]
                elif self.truncation_side == "right":
                    overflowing_tokens = ids[-window_len:]
                    ids = ids[:-num_tokens_to_remove]
                else:
                    raise ValueError(f"invalid truncation strategy: {self.truncation_side}, use 'left' or 'right'.")

            else:
                error_msg = (
                    f"We need to remove {num_tokens_to_remove} to truncate the input "
                    f"but the first sequence has a length {len(ids)}. "
                )
                if truncation_strategy == TruncationStrategy.ONLY_FIRST:
                    error_msg = (
                        error_msg + "Please select another truncation strategy than "
                        f"{truncation_strategy}, for instance 'longest_first' or 'only_second'."
                    )
                logger.error(error_msg)
        elif truncation_strategy == TruncationStrategy.LONGEST_FIRST:
            logger.warning(
                "Be aware, overflowing tokens are not returned for the setting you have chosen,"
                f" i.e. sequence pairs with the '{TruncationStrategy.LONGEST_FIRST.value}' "
                "truncation strategy. So the returned list will always be empty even if some "
                "tokens have been removed."
            )
            for _ in range(num_tokens_to_remove):
                if pair_ids is None or len(ids) > len(pair_ids):
                    if self.truncation_side == "right":
                        ids = ids[:-1]
                    elif self.truncation_side == "left":
                        ids = ids[1:]
                    else:
                        raise ValueError("invalid truncation strategy:" + str(self.truncation_side))
                else:
                    if self.truncation_side == "right":
                        pair_ids = pair_ids[:-1]
                    elif self.truncation_side == "left":
                        pair_ids = pair_ids[1:]
                    else:
                        raise ValueError("invalid truncation strategy:" + str(self.truncation_side))
        elif truncation_strategy == TruncationStrategy.ONLY_SECOND and pair_ids is not None:
            if len(pair_ids) > num_tokens_to_remove:
                window_len = min(len(pair_ids), stride + num_tokens_to_remove)
                if self.truncation_side == "right":
                    overflowing_tokens = pair_ids[-window_len:]
                    pair_ids = pair_ids[:-num_tokens_to_remove]
                elif self.truncation_side == "left":
                    overflowing_tokens = pair_ids[:window_len]
                    pair_ids = pair_ids[num_tokens_to_remove:]
                else:
                    raise ValueError("invalid truncation strategy:" + str(self.truncation_side))
            else:
                logger.error(
                    f"We need to remove {num_tokens_to_remove} to truncate the input "
                    f"but the second sequence has a length {len(pair_ids)}. "
                    f"Please select another truncation strategy than {truncation_strategy}, "
                    "for instance 'longest_first' or 'only_first'."
                )

        return (ids, pair_ids, overflowing_tokens)

    def _pad(
        self,
        encoded_inputs: Union[Dict[str, EncodedInput], BatchEncoding],
        max_length: Optional[int] = None,
        padding_strategy: PaddingStrategy = PaddingStrategy.DO_NOT_PAD,
        pad_to_multiple_of: Optional[int] = None,
        return_attention_mask: Optional[bool] = None,
    ) -> dict:
        """
        Pad encoded inputs (on left/right and up to predefined length or max length in the batch)

        Args:
            encoded_inputs:
                Dictionary of tokenized inputs (`List[int]`) or batch of tokenized inputs (`List[List[int]]`).
            max_length: maximum length of the returned list and optionally padding length (see below).
                Will truncate by taking into account the special tokens.
            padding_strategy: PaddingStrategy to use for padding.

                - PaddingStrategy.LONGEST Pad to the longest sequence in the batch
                - PaddingStrategy.MAX_LENGTH: Pad to the max length (default)
                - PaddingStrategy.DO_NOT_PAD: Do not pad
                The tokenizer padding sides are defined in self.padding_side:

                - 'left': pads on the left of the sequences
                - 'right': pads on the right of the sequences
            pad_to_multiple_of: (optional) Integer if set will pad the sequence to a multiple of the provided value.
                This is especially useful to enable the use of Tensor Core on NVIDIA hardware with compute capability
                `>= 7.5` (Volta).
            return_attention_mask:
                (optional) Set to False to avoid returning attention mask (default: set to model specifics)
        """
        # Load from model defaults
        if return_attention_mask is None:
            return_attention_mask = "attention_mask" in self.model_input_names

        required_input = encoded_inputs[self.model_input_names[0]]

        if padding_strategy == PaddingStrategy.LONGEST:
            max_length = len(required_input)

        if max_length is not None and pad_to_multiple_of is not None and (max_length % pad_to_multiple_of != 0):
            max_length = ((max_length // pad_to_multiple_of) + 1) * pad_to_multiple_of

        needs_to_be_padded = padding_strategy != PaddingStrategy.DO_NOT_PAD and len(required_input) != max_length

        # Initialize attention mask if not present.
        if return_attention_mask and "attention_mask" not in encoded_inputs:
            encoded_inputs["attention_mask"] = [1] * len(required_input)

        if needs_to_be_padded:
            difference = max_length - len(required_input)

            if self.padding_side == "right":
                if return_attention_mask:
                    encoded_inputs["attention_mask"] = encoded_inputs["attention_mask"] + [0] * difference
                if "token_type_ids" in encoded_inputs:
                    encoded_inputs["token_type_ids"] = (
                        encoded_inputs["token_type_ids"] + [self.pad_token_type_id] * difference
                    )
                if "special_tokens_mask" in encoded_inputs:
                    encoded_inputs["special_tokens_mask"] = encoded_inputs["special_tokens_mask"] + [1] * difference
                encoded_inputs[self.model_input_names[0]] = required_input + [self.pad_token_id] * difference
            elif self.padding_side == "left":
                if return_attention_mask:
                    encoded_inputs["attention_mask"] = [0] * difference + encoded_inputs["attention_mask"]
                if "token_type_ids" in encoded_inputs:
                    encoded_inputs["token_type_ids"] = [self.pad_token_type_id] * difference + encoded_inputs[
                        "token_type_ids"
                    ]
                if "special_tokens_mask" in encoded_inputs:
                    encoded_inputs["special_tokens_mask"] = [1] * difference + encoded_inputs["special_tokens_mask"]
                encoded_inputs[self.model_input_names[0]] = [self.pad_token_id] * difference + required_input
            else:
                raise ValueError("Invalid padding strategy:" + str(self.padding_side))

        return encoded_inputs

    def convert_tokens_to_string(self, tokens: List[str]) -> str:
        """
        Converts a sequence of tokens in a single string. The most simple way to do it is `" ".join(tokens)` but we
        often want to remove sub-word tokenization artifacts at the same time.

        Args:
            tokens (`List[str]`): The token to join in a string.

        Returns:
            `str`: The joined tokens.
        """
        raise NotImplementedError

    def batch_decode(
        self,
        sequences: Union[List[int], List[List[int]], "np.ndarray", "mindspore.Tensor"],
        skip_special_tokens: bool = False,
        clean_up_tokenization_spaces: bool = None,
        **kwargs,
    ) -> List[str]:
        """
        Convert a list of lists of token ids into a list of strings by calling decode.

        Args:
            sequences (`Union[List[int], List[List[int]], np.ndarray, mindspore.Tensor, tf.Tensor]`):
                List of tokenized input ids. Can be obtained using the `__call__` method.
            skip_special_tokens (`bool`, *optional*, defaults to `False`):
                Whether or not to remove special tokens in the decoding.
            clean_up_tokenization_spaces (`bool`, *optional*):
                Whether or not to clean up the tokenization spaces. If `None`, will default to
                `self.clean_up_tokenization_spaces`.
            kwargs (additional keyword arguments, *optional*):
                Will be passed to the underlying model specific decode method.

        Returns:
            `List[str]`: The list of decoded sentences.
        """
        return [
            self.decode(
                seq,
                skip_special_tokens=skip_special_tokens,
                clean_up_tokenization_spaces=clean_up_tokenization_spaces,
                **kwargs,
            )
            for seq in sequences
        ]

    def decode(
        self,
        token_ids: Union[int, List[int], "np.ndarray", "mindspore.Tensor"],
        skip_special_tokens: bool = False,
        clean_up_tokenization_spaces: bool = None,
        **kwargs,
    ) -> str:
        """
        Converts a sequence of ids in a string, using the tokenizer and vocabulary with options to remove special
        tokens and clean up tokenization spaces.

        Similar to doing `self.convert_tokens_to_string(self.convert_ids_to_tokens(token_ids))`.

        Args:
            token_ids (`Union[int, List[int], np.ndarray, mindspore.Tensor, tf.Tensor]`):
                List of tokenized input ids. Can be obtained using the `__call__` method.
            skip_special_tokens (`bool`, *optional*, defaults to `False`):
                Whether or not to remove special tokens in the decoding.
            clean_up_tokenization_spaces (`bool`, *optional*):
                Whether or not to clean up the tokenization spaces. If `None`, will default to
                `self.clean_up_tokenization_spaces`.
            kwargs (additional keyword arguments, *optional*):
                Will be passed to the underlying model specific decode method.

        Returns:
            `str`: The decoded sentence.
        """
        # Convert inputs to python lists
        token_ids = to_py_obj(token_ids)

        return self._decode(
            token_ids=token_ids,
            skip_special_tokens=skip_special_tokens,
            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
            **kwargs,
        )

    def _decode(
        self,
        token_ids: Union[int, List[int]],
        skip_special_tokens: bool = False,
        clean_up_tokenization_spaces: bool = None,
        **kwargs,
    ) -> str:
        r"""
        Decode the given token IDs into a string representation.

        Args:
            self (PreTrainedTokenizerBase): The instance of the PreTrainedTokenizerBase class.
            token_ids (Union[int, List[int]]): The token IDs to be decoded into a string. It can be either an integer or a list of integers.
            skip_special_tokens (bool, optional): Whether to skip special tokens during decoding. Defaults to False.
            clean_up_tokenization_spaces (bool, optional): Whether to clean up tokenization spaces during decoding. Defaults to None.
            **kwargs: Additional keyword arguments for future compatibility.

        Returns:
            str: The decoded string representation of the given token IDs.

        Raises:
            NotImplementedError: If the method is not implemented.

        Note:
            The method decodes the token IDs into a string using the tokenizer's decoding logic. Special tokens and
            tokenization spaces can be skipped or cleaned up if specified.
        """
        raise NotImplementedError

    def get_special_tokens_mask(
        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
    ) -> List[int]:
        """
        Retrieves sequence ids from a token list that has no special tokens added. This method is called when adding
        special tokens using the tokenizer `prepare_for_model` or `encode_plus` methods.

        Args:
            token_ids_0 (`List[int]`):
                List of ids of the first sequence.
            token_ids_1 (`List[int]`, *optional*):
                List of ids of the second sequence.
            already_has_special_tokens (`bool`, *optional*, defaults to `False`):
                Whether or not the token list is already formatted with special tokens for the model.

        Returns:
            A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
        """
        assert already_has_special_tokens and token_ids_1 is None, (
            "You cannot use ``already_has_special_tokens=False`` with this tokenizer. "
            "Please use a slow (full python) tokenizer to activate this argument. "
            "Or set `return_special_tokens_mask=True` when calling the encoding method "
            "to get the special tokens mask in any tokenizer. "
        )

        all_special_ids = self.all_special_ids  # cache the property

        special_tokens_mask = [1 if token in all_special_ids else 0 for token in token_ids_0]

        return special_tokens_mask

    @staticmethod
    def clean_up_tokenization(out_string: str) -> str:
        """
        Clean up a list of simple English tokenization artifacts like spaces before punctuations and abbreviated forms.

        Args:
            out_string (`str`): The text to clean up.

        Returns:
            `str`: The cleaned-up string.
        """
        out_string = (
            out_string.replace(" .", ".")
            .replace(" ?", "?")
            .replace(" !", "!")
            .replace(" ,", ",")
            .replace(" ' ", "'")
            .replace(" n't", "n't")
            .replace(" 'm", "'m")
            .replace(" 's", "'s")
            .replace(" 've", "'ve")
            .replace(" 're", "'re")
        )
        return out_string

    def _eventual_warn_about_too_long_sequence(self, ids: List[int], max_length: Optional[int], verbose: bool):
        """
        Depending on the input and internal state we might trigger a warning about a sequence that is too long for its
        corresponding model

        Args:
            ids (`List[str]`): The ids produced by the tokenization
            max_length (`int`, *optional*): The max_length desired (does not trigger a warning if it is set)
            verbose (`bool`): Whether or not to print more information and warnings.

        """
        if max_length is None and len(ids) > self.model_max_length and verbose:
            if not self.deprecation_warnings.get("sequence-length-is-longer-than-the-specified-maximum", False):
                logger.warning(
                    "Token indices sequence length is longer than the specified maximum sequence length "
                    f"for this model ({len(ids)} > {self.model_max_length}). Running this sequence through the model "
                    "will result in indexing errors"
                )
            self.deprecation_warnings["sequence-length-is-longer-than-the-specified-maximum"] = True

    def _switch_to_input_mode(self):
        """
        Private method to put the tokenizer in input mode (when it has different modes for input/outputs)
        """
    def _switch_to_target_mode(self):
        """
        Private method to put the tokenizer in target mode (when it has different modes for input/outputs)
        """
    @contextmanager
    def as_target_tokenizer(self):
        """
        Temporarily sets the tokenizer for encoding the targets. Useful for tokenizer associated to
        sequence-to-sequence models that need a slightly different processing for the labels.
        """
        warnings.warn(
            "`as_target_tokenizer` is deprecated and will be removed in v5 of Transformers. You can tokenize your "
            "labels by using the argument `text_target` of the regular `__call__` method (either in the same call as "
            "your input texts if you use the same keyword arguments, or in a separate call."
        )
        self._switch_to_target_mode()
        self._in_target_context_manager = True
        yield
        self._in_target_context_manager = False
        self._switch_to_input_mode()

    @classmethod
    def register_for_auto_class(cls, auto_class="AutoTokenizer"):
        """
        Register this class with a given auto class. This should only be used for custom tokenizers as the ones in the
        library are already mapped with `AutoTokenizer`.

        <Tip warning={true}>

        This API is experimental and may have some slight breaking changes in the next releases.

        </Tip>

        Args:
            auto_class (`str` or `type`, *optional*, defaults to `"AutoTokenizer"`):
                The auto class to register this new tokenizer with.
        """
        if not isinstance(auto_class, str):
            auto_class = auto_class.__name__

        import mindnlp.transformers.models.auto as auto_module

        if not hasattr(auto_module, auto_class):
            raise ValueError(f"{auto_class} is not a valid auto class.")

        cls._auto_class = auto_class

    def prepare_seq2seq_batch(
        self,
        src_texts: List[str],
        tgt_texts: Optional[List[str]] = None,
        max_length: Optional[int] = None,
        max_target_length: Optional[int] = None,
        padding: str = "longest",
        return_tensors: str = None,
        truncation: bool = True,
        **kwargs,
    ) -> BatchEncoding:
        """
        Prepare model inputs for translation. For best performance, translate one sentence at a time.

        Arguments:
            src_texts (`List[str]`):
                List of documents to summarize or source language texts.
            tgt_texts (`list`, *optional*):
                List of summaries or target language texts.
            max_length (`int`, *optional*):
                Controls the maximum length for encoder inputs (documents to summarize or source language texts) If
                left unset or set to `None`, this will use the predefined model maximum length if a maximum length is
                required by one of the truncation/padding parameters. If the model has no specific maximum input length
                (like XLNet) truncation/padding to a maximum length will be deactivated.
            max_target_length (`int`, *optional*):
                Controls the maximum length of decoder inputs (target language texts or summaries) If left unset or set
                to `None`, this will use the max_length value.
            padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `False`):
                Activates and controls padding. Accepts the following values:

                - `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single
                  sequence if provided).
                - `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum
                  acceptable input length for the model if that argument is not provided.
                - `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different
                  lengths).
            return_tensors (`str` or [`~utils.TensorType`], *optional*):
                If set, will return tensors instead of list of python integers. Acceptable values are:

                - `'tf'`: Return TensorFlow `tf.constant` objects.
                - `'pt'`: Return PyTorch `mindspore.Tensor` objects.
                - `'np'`: Return Numpy `np.ndarray` objects.
            truncation (`bool`, `str` or [`~tokenization_utils_base.TruncationStrategy`], *optional*, defaults to `True`):
                Activates and controls truncation. Accepts the following values:

                - `True` or `'longest_first'`: Truncate to a maximum length specified with the argument `max_length` or
                  to the maximum acceptable input length for the model if that argument is not provided. This will
                  truncate token by token, removing a token from the longest sequence in the pair if a pair of
                  sequences (or a batch of pairs) is provided.
                - `'only_first'`: Truncate to a maximum length specified with the argument `max_length` or to the
                  maximum acceptable input length for the model if that argument is not provided. This will only
                  truncate the first sequence of a pair if a pair of sequences (or a batch of pairs) is provided.
                - `'only_second'`: Truncate to a maximum length specified with the argument `max_length` or to the
                  maximum acceptable input length for the model if that argument is not provided. This will only
                  truncate the second sequence of a pair if a pair of sequences (or a batch of pairs) is provided.
                - `False` or `'do_not_truncate'` (default): No truncation (i.e., can output batch with sequence lengths
                  greater than the model maximum admissible input size).
            **kwargs:
                Additional keyword arguments passed along to `self.__call__`.

        Returns:
            [`BatchEncoding`]: A [`BatchEncoding`] with the following fields:

            - **input_ids** -- List of token ids to be fed to the encoder.
            - **attention_mask** -- List of indices specifying which tokens should be attended to by the model.
            - **labels** -- List of token ids for tgt_texts.

            The full set of keys `[input_ids, attention_mask, labels]`, will only be returned if tgt_texts is passed.
            Otherwise, input_ids, attention_mask will be the only keys.
        """
        # docstyle-ignore
        formatted_warning = """
`prepare_seq2seq_batch` is deprecated and will be removed in version 5 of HuggingFace Transformers. Use the regular
`__call__` method to prepare your inputs and targets.

Here is a short example:

model_inputs = tokenizer(src_texts, text_target=tgt_texts, ...)

If you either need to use different keyword arguments for the source and target texts, you should do two calls like
this:

model_inputs = tokenizer(src_texts, ...)
labels = tokenizer(text_target=tgt_texts, ...)
model_inputs["labels"] = labels["input_ids"]

See the documentation of your specific tokenizer for more details on the specific arguments to the tokenizer of choice.
For a more complete example, see the implementation of `prepare_seq2seq_batch`.
"""
        warnings.warn(formatted_warning, FutureWarning)
        # mBART-specific kwargs that should be ignored by other models.
        kwargs.pop("src_lang", None)
        kwargs.pop("tgt_lang", None)
        if max_length is None:
            max_length = self.model_max_length
        model_inputs = self(
            src_texts,
            add_special_tokens=True,
            return_tensors=return_tensors,
            max_length=max_length,
            padding=padding,
            truncation=truncation,
            **kwargs,
        )
        if tgt_texts is None:
            return model_inputs
        # Process tgt_texts
        if max_target_length is None:
            max_target_length = max_length
        with self.as_target_tokenizer():
            labels = self(
                tgt_texts,
                add_special_tokens=True,
                return_tensors=return_tensors,
                padding=padding,
                max_length=max_target_length,
                truncation=truncation,
                **kwargs,
            )
        model_inputs["labels"] = labels["input_ids"]
        return model_inputs

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.added_tokens_decoder: Dict[int, AddedToken] property

Method to retrieve the decoder mapping for added tokens.

PARAMETER	DESCRIPTION
self	The instance of the PreTrainedTokenizerBase class. It represents the tokenizer object for which the added tokens decoder is being retrieved. TYPE: PreTrainedTokenizerBase

RETURNS	DESCRIPTION
Dict[int, AddedToken]	Dict[int, AddedToken]: A dictionary mapping integer indices to AddedToken objects. The AddedToken objects correspond to additional tokens that were added to the tokenizer.

RAISES	DESCRIPTION
NotImplementedError	This exception is raised if the method is called and not implemented in the subclass.

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.default_chat_template property

This template formats inputs in the standard ChatML format. See https://github.com/openai/openai-python/blob/main/chatml.md

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.max_len_sentences_pair: int property writable

int: The maximum combined length of a pair of sentences that can be fed to the model.

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.max_len_single_sentence: int property writable

int: The maximum length of a sentence that can be fed to the model.

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.__call__(text=None, text_pair=None, text_target=None, text_pair_target=None, add_special_tokens=True, padding=False, truncation=None, max_length=None, stride=0, is_split_into_words=False, pad_to_multiple_of=None, return_tensors=None, return_token_type_ids=None, return_attention_mask=None, return_overflowing_tokens=False, return_special_tokens_mask=False, return_offsets_mapping=False, return_length=False, verbose=True, **kwargs)

Main method to tokenize and prepare for the model one or several sequence(s) or one or several pair(s) of sequences.

PARAMETER	DESCRIPTION
text	The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set is_split_into_words=True (to lift the ambiguity with a batch of sequences). TYPE: `str`, `List[str]`, `List[List[str]]`, *optional* DEFAULT: None
text_pair	The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set is_split_into_words=True (to lift the ambiguity with a batch of sequences). TYPE: `str`, `List[str]`, `List[List[str]]`, *optional* DEFAULT: None
text_target	The sequence or batch of sequences to be encoded as target texts. Each sequence can be a string or a list of strings (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set is_split_into_words=True (to lift the ambiguity with a batch of sequences). TYPE: `str`, `List[str]`, `List[List[str]]`, *optional* DEFAULT: None
text_pair_target	The sequence or batch of sequences to be encoded as target texts. Each sequence can be a string or a list of strings (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set is_split_into_words=True (to lift the ambiguity with a batch of sequences). TYPE: `str`, `List[str]`, `List[List[str]]`, *optional* DEFAULT: None

Source code in mindnlp/transformers/tokenization_utils_base.py

def __call__(
    self,
    text: Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]] = None,
    text_pair: Optional[Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]]] = None,
    text_target: Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]] = None,
    text_pair_target: Optional[
        Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]]
    ] = None,
    add_special_tokens: bool = True,
    padding: Union[bool, str, PaddingStrategy] = False,
    truncation: Union[bool, str, TruncationStrategy] = None,
    max_length: Optional[int] = None,
    stride: int = 0,
    is_split_into_words: bool = False,
    pad_to_multiple_of: Optional[int] = None,
    return_tensors: Optional[Union[str, TensorType]] = None,
    return_token_type_ids: Optional[bool] = None,
    return_attention_mask: Optional[bool] = None,
    return_overflowing_tokens: bool = False,
    return_special_tokens_mask: bool = False,
    return_offsets_mapping: bool = False,
    return_length: bool = False,
    verbose: bool = True,
    **kwargs,
) -> BatchEncoding:
    """
    Main method to tokenize and prepare for the model one or several sequence(s) or one or several pair(s) of
    sequences.

    Args:
        text (`str`, `List[str]`, `List[List[str]]`, *optional*):
            The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings
            (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
            `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
        text_pair (`str`, `List[str]`, `List[List[str]]`, *optional*):
            The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings
            (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
            `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
        text_target (`str`, `List[str]`, `List[List[str]]`, *optional*):
            The sequence or batch of sequences to be encoded as target texts. Each sequence can be a string or a
            list of strings (pretokenized string). If the sequences are provided as list of strings (pretokenized),
            you must set `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
        text_pair_target (`str`, `List[str]`, `List[List[str]]`, *optional*):
            The sequence or batch of sequences to be encoded as target texts. Each sequence can be a string or a
            list of strings (pretokenized string). If the sequences are provided as list of strings (pretokenized),
            you must set `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
    """
    # To avoid duplicating
    all_kwargs = {
        "add_special_tokens": add_special_tokens,
        "padding": padding,
        "truncation": truncation,
        "max_length": max_length,
        "stride": stride,
        "is_split_into_words": is_split_into_words,
        "pad_to_multiple_of": pad_to_multiple_of,
        "return_tensors": return_tensors,
        "return_token_type_ids": return_token_type_ids,
        "return_attention_mask": return_attention_mask,
        "return_overflowing_tokens": return_overflowing_tokens,
        "return_special_tokens_mask": return_special_tokens_mask,
        "return_offsets_mapping": return_offsets_mapping,
        "return_length": return_length,
        "verbose": verbose,
    }
    all_kwargs.update(kwargs)
    if text is None and text_target is None:
        raise ValueError("You need to specify either `text` or `text_target`.")
    if text is not None:
        # for mindspore.dataset
        if isinstance(text, np.ndarray):
            text = str(text)
            if isinstance(text_pair, np.ndarray):
                text_pair = str(text_pair)
            elif isinstance(text_pair, list):
                text_pair = [str(t) for t in text_pair]
        # The context manager will send the inputs as normal texts and not text_target, but we shouldn't change the
        # input mode in this case.
        if not self._in_target_context_manager:
            self._switch_to_input_mode()
        encodings = self._call_one(text=text, text_pair=text_pair, **all_kwargs)
    if text_target is not None:
        self._switch_to_target_mode()
        target_encodings = self._call_one(text=text_target, text_pair=text_pair_target, **all_kwargs)
    # Leave back tokenizer in input mode
    self._switch_to_input_mode()

    if text_target is None:
        return encodings
    if text is None:
        return target_encodings
    encodings["labels"] = target_encodings["input_ids"]
    return encodings

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.__init__(**kwargs)

Initialize the PreTrainedTokenizerBase class.

PARAMETER	DESCRIPTION
self	The instance of the class.

RETURNS	DESCRIPTION
	None.

RAISES	DESCRIPTION
ValueError	If the provided padding_side or truncation_side is not one of ['right', 'left'].

Source code in mindnlp/transformers/tokenization_utils_base.py

def __init__(self, **kwargs):
    r"""
    Initialize the PreTrainedTokenizerBase class.

    Args:
        self: The instance of the class.

    Returns:
        None.

    Raises:
        ValueError: If the provided padding_side or truncation_side is not one of ['right', 'left'].
    """
    # inputs and kwargs for saving and re-loading (see ``from_pretrained`` and ``save_pretrained``)
    self.init_inputs = ()
    self.init_kwargs = copy.deepcopy(kwargs)
    self.name_or_path = kwargs.pop("name_or_path", "")
    self._processor_class = kwargs.pop("processor_class", None)

    # For backward compatibility we fallback to set model_max_length from max_len if provided
    model_max_length = kwargs.pop("model_max_length", kwargs.pop("max_len", None))
    self.model_max_length = model_max_length if model_max_length is not None else VERY_LARGE_INTEGER

    # Padding and truncation side are right by default and overridden in subclasses. If specified in the kwargs, it
    # is changed.
    self.padding_side = kwargs.pop("padding_side", self.padding_side)
    if self.padding_side not in ["right", "left"]:
        raise ValueError(
            f"Padding side should be selected between 'right' and 'left', current value: {self.padding_side}"
        )

    self.truncation_side = kwargs.pop("truncation_side", self.truncation_side)
    if self.truncation_side not in ["right", "left"]:
        raise ValueError(
            f"Padding side should be selected between 'right' and 'left', current value: {self.truncation_side}"
        )

    self.model_input_names = kwargs.pop("model_input_names", self.model_input_names)

    # By default, cleaning tokenization spaces for both fast and slow tokenizers
    self.clean_up_tokenization_spaces = kwargs.pop("clean_up_tokenization_spaces", True)

    # By default, do not split special tokens for both fast and slow tokenizers
    self.split_special_tokens = kwargs.pop("split_special_tokens", False)

    self.deprecation_warnings = (
        {}
    )  # Use to store when we have already noticed a deprecation warning (avoid overlogging).
    self._in_target_context_manager = False

    # Stores a Jinja template that formats chat histories into tokenizable strings
    self.chat_template = kwargs.pop("chat_template", None)

    super().__init__(**kwargs)

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.__len__()

Method 'len' in the class 'PreTrainedTokenizerBase'.

PARAMETER	DESCRIPTION
self	A reference to the instance of the class. It is automatically passed when the method is called. No additional arguments are expected.

RETURNS	DESCRIPTION
int	An integer value representing the length of the object. This method is intended to be overridden by subclasses to provide custom length calculation logic.

RAISES	DESCRIPTION
NotImplementedError	This exception is raised to indicate that the method is not implemented in the current class and should be implemented in subclasses.

Source code in mindnlp/transformers/tokenization_utils_base.py

def __len__(self) -> int:
    r"""
    Method '__len__' in the class 'PreTrainedTokenizerBase'.

    Args:
        self: A reference to the instance of the class.
            It is automatically passed when the method is called. No additional arguments are expected.

    Returns:
        An integer value representing the length of the object.
            This method is intended to be overridden by subclasses to provide custom length calculation logic.

    Raises:
        NotImplementedError:
            This exception is raised to indicate that the method is not implemented in the current class
            and should be implemented in subclasses.
    """
    raise NotImplementedError()

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.__repr__()

This method generates a string representation of the PreTrainedTokenizerBase object.

PARAMETER	DESCRIPTION
self	The instance of the PreTrainedTokenizerBase class.

RETURNS	DESCRIPTION
str	A string representing the object with various attributes such as name_or_path, vocab_size, model_max_length, is_fast, padding_side, truncation_side, special_tokens_map, clean_up_tokenization_spaces, and added_tokens_decoder. The added_tokens_decoder section includes a dictionary representation of added tokens and their respective values. TYPE: str

Source code in mindnlp/transformers/tokenization_utils_base.py

def __repr__(self) -> str:
    r"""
    This method generates a string representation of the PreTrainedTokenizerBase object.

    Args:
        self: The instance of the PreTrainedTokenizerBase class.

    Returns:
        str:
            A string representing the object with various attributes such as
            name_or_path, vocab_size, model_max_length, is_fast, padding_side, truncation_side, special_tokens_map,
            clean_up_tokenization_spaces, and added_tokens_decoder.
            The added_tokens_decoder section includes a dictionary representation of added tokens and their respective values.

    Raises:
        None
    """
    added_tokens_decoder_rep = "\n\t".join([f"{k}: {v.__repr__()}," for k, v in self.added_tokens_decoder.items()])
    return (
        f"{self.__class__.__name__}(name_or_path='{self.name_or_path}',"
        f" vocab_size={self.vocab_size}, model_max_length={self.model_max_length}, is_fast={self.is_fast},"
        f" padding_side='{self.padding_side}', truncation_side='{self.truncation_side}',"
        f" special_tokens={self.special_tokens_map}, clean_up_tokenization_spaces={self.clean_up_tokenization_spaces}), "
        " added_tokens_decoder={\n\t" + added_tokens_decoder_rep + "\n}"
    )

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.apply_chat_template(conversation, chat_template=None, add_generation_prompt=False, tokenize=True, padding=False, truncation=False, max_length=None, return_tensors=None, return_dict=False, **tokenizer_kwargs)

Converts a Conversation object or a list of dictionaries with "role" and "content" keys to a list of token ids. This method is intended for use with chat models, and will read the tokenizer's chat_template attribute to determine the format and control tokens to use when converting. When chat_template is None, it will fall back to the default_chat_template specified at the class level.

PARAMETER	DESCRIPTION
conversation	A Conversation object or list of dicts with "role" and "content" keys, representing the chat history so far. TYPE: Union[List[Dict[str, str]], Conversation]
chat_template	A Jinja template to use for this conversion. If this is not passed, the model's default chat template will be used instead. TYPE: str, *optional* DEFAULT: None
add_generation_prompt	Whether to end the prompt with the token(s) that indicate the start of an assistant message. This is useful when you want to generate a response from the model. Note that this argument will be passed to the chat template, and so it must be supported in the template for this argument to have any effect. TYPE: bool, *optional* DEFAULT: False
tokenize	Whether to tokenize the output. If False, the output will be a string. TYPE: `bool`, defaults to `True` DEFAULT: True
padding	Whether to pad sequences to the maximum length. Has no effect if tokenize is False. TYPE: `bool`, defaults to `False` DEFAULT: False
truncation	Whether to truncate sequences at the maximum length. Has no effect if tokenize is False. TYPE: `bool`, defaults to `False` DEFAULT: False
max_length	Maximum length (in tokens) to use for padding or truncation. Has no effect if tokenize is False. If not specified, the tokenizer's max_length attribute will be used as a default. TYPE: `int`, *optional* DEFAULT: None
return_tensors	If set, will return tensors of a particular framework. Has no effect if tokenize is False. Acceptable values are: 'tf': Return TensorFlow tf.Tensor objects. 'pt': Return PyTorch mindspore.Tensor objects. 'np': Return NumPy np.ndarray objects. 'jax': Return JAX jnp.ndarray objects. TYPE: `str` or [`~utils.TensorType`], *optional* DEFAULT: None
**tokenizer_kwargs	Additional kwargs to pass to the tokenizer. DEFAULT: {}

RETURNS	DESCRIPTION
Union[str, List[int]]	List[int]: A list of token ids representing the tokenized chat so far, including control tokens. This
Union[str, List[int]]	output is ready to pass to the model, either directly or via methods like generate().

Source code in mindnlp/transformers/tokenization_utils_base.py

def apply_chat_template(
    self,
    conversation: Union[List[Dict[str, str]], "Conversation"],
    chat_template: Optional[str] = None,
    add_generation_prompt: bool = False,
    tokenize: bool = True,
    padding: bool = False,
    truncation: bool = False,
    max_length: Optional[int] = None,
    return_tensors: Optional[Union[str, TensorType]] = None,
    return_dict: bool = False,
    **tokenizer_kwargs,
) -> Union[str, List[int]]:
    """
    Converts a Conversation object or a list of dictionaries with `"role"` and `"content"` keys to a list of token
    ids. This method is intended for use with chat models, and will read the tokenizer's chat_template attribute to
    determine the format and control tokens to use when converting. When chat_template is None, it will fall back
    to the default_chat_template specified at the class level.

    Args:
        conversation (Union[List[Dict[str, str]], "Conversation"]): A Conversation object or list of dicts
            with "role" and "content" keys, representing the chat history so far.
        chat_template (str, *optional*): A Jinja template to use for this conversion. If
            this is not passed, the model's default chat template will be used instead.
        add_generation_prompt (bool, *optional*): Whether to end the prompt with the token(s) that indicate
            the start of an assistant message. This is useful when you want to generate a response from the model.
            Note that this argument will be passed to the chat template, and so it must be supported in the
            template for this argument to have any effect.
        tokenize (`bool`, defaults to `True`):
            Whether to tokenize the output. If `False`, the output will be a string.
        padding (`bool`, defaults to `False`):
            Whether to pad sequences to the maximum length. Has no effect if tokenize is `False`.
        truncation (`bool`, defaults to `False`):
            Whether to truncate sequences at the maximum length. Has no effect if tokenize is `False`.
        max_length (`int`, *optional*):
            Maximum length (in tokens) to use for padding or truncation. Has no effect if tokenize is `False`. If
            not specified, the tokenizer's `max_length` attribute will be used as a default.
        return_tensors (`str` or [`~utils.TensorType`], *optional*):
            If set, will return tensors of a particular framework. Has no effect if tokenize is `False`. Acceptable
            values are:

            - `'tf'`: Return TensorFlow `tf.Tensor` objects.
            - `'pt'`: Return PyTorch `mindspore.Tensor` objects.
            - `'np'`: Return NumPy `np.ndarray` objects.
            - `'jax'`: Return JAX `jnp.ndarray` objects.
        **tokenizer_kwargs: Additional kwargs to pass to the tokenizer.

    Returns:
        `List[int]`: A list of token ids representing the tokenized chat so far, including control tokens. This
        output is ready to pass to the model, either directly or via methods like `generate()`.
    """
    if hasattr(conversation, "messages"):
        # Indicates it's a Conversation object
        conversation = conversation.messages

    # priority: `chat_template` argument > `tokenizer.chat_template` > `tokenizer.default_chat_template`
    if chat_template is None:
        if self.chat_template is not None:
            chat_template = self.chat_template
        else:
            chat_template = self.default_chat_template

    # Compilation function uses a cache to avoid recompiling the same template
    compiled_template = self._compile_jinja_template(chat_template)

    rendered = compiled_template.render(
        messages=conversation, add_generation_prompt=add_generation_prompt, **self.special_tokens_map
    )

    if padding is True:
        padding = "max_length"  # There's only one sequence here, so "longest" makes no sense
    if tokenize:
        if return_dict:
            return self(
                rendered,
                padding=padding,
                truncation=truncation,
                max_length=max_length,
                add_special_tokens=False,
                return_tensors=return_tensors,
                **tokenizer_kwargs,
            )

        return self.encode(
            rendered,
            padding=padding,
            truncation=truncation,
            max_length=max_length,
            add_special_tokens=False,
            return_tensors=return_tensors,
            **tokenizer_kwargs,
        )
    return rendered

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.as_target_tokenizer()

Temporarily sets the tokenizer for encoding the targets. Useful for tokenizer associated to sequence-to-sequence models that need a slightly different processing for the labels.

Source code in mindnlp/transformers/tokenization_utils_base.py

@contextmanager
def as_target_tokenizer(self):
    """
    Temporarily sets the tokenizer for encoding the targets. Useful for tokenizer associated to
    sequence-to-sequence models that need a slightly different processing for the labels.
    """
    warnings.warn(
        "`as_target_tokenizer` is deprecated and will be removed in v5 of Transformers. You can tokenize your "
        "labels by using the argument `text_target` of the regular `__call__` method (either in the same call as "
        "your input texts if you use the same keyword arguments, or in a separate call."
    )
    self._switch_to_target_mode()
    self._in_target_context_manager = True
    yield
    self._in_target_context_manager = False
    self._switch_to_input_mode()

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.batch_decode(sequences, skip_special_tokens=False, clean_up_tokenization_spaces=None, **kwargs)

Convert a list of lists of token ids into a list of strings by calling decode.

PARAMETER	DESCRIPTION
sequences	List of tokenized input ids. Can be obtained using the __call__ method. TYPE: `Union[List[int], List[List[int]], np.ndarray, mindspore.Tensor, tf.Tensor]`
skip_special_tokens	Whether or not to remove special tokens in the decoding. TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False
clean_up_tokenization_spaces	Whether or not to clean up the tokenization spaces. If None, will default to self.clean_up_tokenization_spaces. TYPE: `bool`, *optional* DEFAULT: None
kwargs	Will be passed to the underlying model specific decode method. TYPE: additional keyword arguments, *optional* DEFAULT: {}

RETURNS	DESCRIPTION
List[str]	List[str]: The list of decoded sentences.

Source code in mindnlp/transformers/tokenization_utils_base.py

def batch_decode(
    self,
    sequences: Union[List[int], List[List[int]], "np.ndarray", "mindspore.Tensor"],
    skip_special_tokens: bool = False,
    clean_up_tokenization_spaces: bool = None,
    **kwargs,
) -> List[str]:
    """
    Convert a list of lists of token ids into a list of strings by calling decode.

    Args:
        sequences (`Union[List[int], List[List[int]], np.ndarray, mindspore.Tensor, tf.Tensor]`):
            List of tokenized input ids. Can be obtained using the `__call__` method.
        skip_special_tokens (`bool`, *optional*, defaults to `False`):
            Whether or not to remove special tokens in the decoding.
        clean_up_tokenization_spaces (`bool`, *optional*):
            Whether or not to clean up the tokenization spaces. If `None`, will default to
            `self.clean_up_tokenization_spaces`.
        kwargs (additional keyword arguments, *optional*):
            Will be passed to the underlying model specific decode method.

    Returns:
        `List[str]`: The list of decoded sentences.
    """
    return [
        self.decode(
            seq,
            skip_special_tokens=skip_special_tokens,
            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
            **kwargs,
        )
        for seq in sequences
    ]

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.batch_encode_plus(batch_text_or_text_pairs, add_special_tokens=True, padding=False, truncation=None, max_length=None, stride=0, is_split_into_words=False, pad_to_multiple_of=None, return_tensors=None, return_token_type_ids=None, return_attention_mask=None, return_overflowing_tokens=False, return_special_tokens_mask=False, return_offsets_mapping=False, return_length=False, verbose=True, **kwargs)

Tokenize and prepare for the model a list of sequences or a list of pairs of sequences.

This method is deprecated, __call__ should be used instead.

PARAMETER	DESCRIPTION
also	Batch of sequences or pair of sequences to be encoded. This can be a list of string/string-sequences/int-sequences or a list of pair of string/string-sequences/int-sequence (see details in encode_plus). TYPE: `List[List[int]]`, `List[Tuple[List[int], List[int]]]`

Source code in mindnlp/transformers/tokenization_utils_base.py

def batch_encode_plus(
    self,
    batch_text_or_text_pairs: Union[
        List[TextInput],
        List[TextInputPair],
        List[PreTokenizedInput],
        List[PreTokenizedInputPair],
        List[EncodedInput],
        List[EncodedInputPair],
    ],
    add_special_tokens: bool = True,
    padding: Union[bool, str, PaddingStrategy] = False,
    truncation: Union[bool, str, TruncationStrategy] = None,
    max_length: Optional[int] = None,
    stride: int = 0,
    is_split_into_words: bool = False,
    pad_to_multiple_of: Optional[int] = None,
    return_tensors: Optional[Union[str, TensorType]] = None,
    return_token_type_ids: Optional[bool] = None,
    return_attention_mask: Optional[bool] = None,
    return_overflowing_tokens: bool = False,
    return_special_tokens_mask: bool = False,
    return_offsets_mapping: bool = False,
    return_length: bool = False,
    verbose: bool = True,
    **kwargs,
) -> BatchEncoding:
    """
    Tokenize and prepare for the model a list of sequences or a list of pairs of sequences.

    <Tip warning={true}>

    This method is deprecated, `__call__` should be used instead.

    </Tip>

    Args:
        batch_text_or_text_pairs (`List[str]`, `List[Tuple[str, str]]`, `List[List[str]]`, `List[Tuple[List[str], List[str]]]`, and for not-fast tokenizers,
        also `List[List[int]]`, `List[Tuple[List[int], List[int]]]`):
            Batch of sequences or pair of sequences to be encoded. This can be a list of
            string/string-sequences/int-sequences or a list of pair of string/string-sequences/int-sequence (see
            details in `encode_plus`).
    """
    # Backward compatibility for 'truncation_strategy', 'pad_to_max_length'
    padding_strategy, truncation_strategy, max_length, kwargs = self._get_padding_truncation_strategies(
        padding=padding,
        truncation=truncation,
        max_length=max_length,
        pad_to_multiple_of=pad_to_multiple_of,
        verbose=verbose,
        **kwargs,
    )

    return self._batch_encode_plus(
        batch_text_or_text_pairs=batch_text_or_text_pairs,
        add_special_tokens=add_special_tokens,
        padding_strategy=padding_strategy,
        truncation_strategy=truncation_strategy,
        max_length=max_length,
        stride=stride,
        is_split_into_words=is_split_into_words,
        pad_to_multiple_of=pad_to_multiple_of,
        return_tensors=return_tensors,
        return_token_type_ids=return_token_type_ids,
        return_attention_mask=return_attention_mask,
        return_overflowing_tokens=return_overflowing_tokens,
        return_special_tokens_mask=return_special_tokens_mask,
        return_offsets_mapping=return_offsets_mapping,
        return_length=return_length,
        verbose=verbose,
        **kwargs,
    )

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.build_inputs_with_special_tokens(token_ids_0, token_ids_1=None)

Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens.

This implementation does not add special tokens and this method should be overridden in a subclass.

PARAMETER	DESCRIPTION
token_ids_0	The first tokenized sequence. TYPE: `List[int]`
token_ids_1	The second tokenized sequence. TYPE: `List[int]`, *optional* DEFAULT: None

RETURNS	DESCRIPTION
List[int]	List[int]: The model input with special tokens.

Source code in mindnlp/transformers/tokenization_utils_base.py

def build_inputs_with_special_tokens(
    self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
) -> List[int]:
    """
    Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
    adding special tokens.

    This implementation does not add special tokens and this method should be overridden in a subclass.

    Args:
        token_ids_0 (`List[int]`): The first tokenized sequence.
        token_ids_1 (`List[int]`, *optional*): The second tokenized sequence.

    Returns:
        `List[int]`: The model input with special tokens.
    """
    if token_ids_1 is None:
        return token_ids_0
    return token_ids_0 + token_ids_1

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.clean_up_tokenization(out_string) staticmethod

Clean up a list of simple English tokenization artifacts like spaces before punctuations and abbreviated forms.

PARAMETER	DESCRIPTION
out_string	The text to clean up. TYPE: `str`

RETURNS	DESCRIPTION
str	str: The cleaned-up string.

Source code in mindnlp/transformers/tokenization_utils_base.py

@staticmethod
def clean_up_tokenization(out_string: str) -> str:
    """
    Clean up a list of simple English tokenization artifacts like spaces before punctuations and abbreviated forms.

    Args:
        out_string (`str`): The text to clean up.

    Returns:
        `str`: The cleaned-up string.
    """
    out_string = (
        out_string.replace(" .", ".")
        .replace(" ?", "?")
        .replace(" !", "!")
        .replace(" ,", ",")
        .replace(" ' ", "'")
        .replace(" n't", "n't")
        .replace(" 'm", "'m")
        .replace(" 's", "'s")
        .replace(" 've", "'ve")
        .replace(" 're", "'re")
    )
    return out_string

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.convert_added_tokens(obj, save=False, add_type_field=True) classmethod

Converts AddedToken objects to dictionaries and vice versa.

PARAMETER	DESCRIPTION
cls	The class reference. TYPE: type
obj	The object to convert. Can be an AddedToken object, dictionary, list, tuple, or any other type. TYPE: Union[AddedToken, Any]
save	Indicates whether to save the converted object. Default is False. TYPE: bool DEFAULT: False
add_type_field	Indicates whether to add a '__type' field during conversion. Default is True. TYPE: bool DEFAULT: True

RETURNS	DESCRIPTION
None	The method modifies the input object in place or returns a converted object.

RAISES	DESCRIPTION
TypeError	If the obj parameter is of an unsupported type.
KeyError	If the '__type' key is not found in the dictionary object.

Source code in mindnlp/transformers/tokenization_utils_base.py

@classmethod
def convert_added_tokens(cls, obj: Union[AddedToken, Any], save=False, add_type_field=True):
    r"""
    Converts AddedToken objects to dictionaries and vice versa.

    Args:
        cls (type): The class reference.
        obj (Union[AddedToken, Any]):
            The object to convert. Can be an AddedToken object, dictionary, list, tuple, or any other type.
        save (bool): Indicates whether to save the converted object. Default is False.
        add_type_field (bool): Indicates whether to add a '__type' field during conversion. Default is True.

    Returns:
        None: The method modifies the input object in place or returns a converted object.

    Raises:
        TypeError: If the obj parameter is of an unsupported type.
        KeyError: If the '__type' key is not found in the dictionary object.
    """
    if isinstance(obj, dict) and "__type" in obj and obj["__type"] == "AddedToken":
        obj.pop("__type")
        return AddedToken(**obj)
    if isinstance(obj, AddedToken) and save:
        obj = obj.__getstate__()
        if add_type_field:
            obj["__type"] = "AddedToken"
        else:
            # Don't save "special" for previous tokenizers
            obj.pop("special")
        return obj
    if isinstance(obj, (list, tuple)):
        return [cls.convert_added_tokens(o, save=save, add_type_field=add_type_field) for o in obj]
    if isinstance(obj, dict):
        return {k: cls.convert_added_tokens(v, save=save, add_type_field=add_type_field) for k, v in obj.items()}
    return obj

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.convert_tokens_to_string(tokens)

Converts a sequence of tokens in a single string. The most simple way to do it is " ".join(tokens) but we often want to remove sub-word tokenization artifacts at the same time.

PARAMETER	DESCRIPTION
tokens	The token to join in a string. TYPE: `List[str]`

RETURNS	DESCRIPTION
str	str: The joined tokens.

Source code in mindnlp/transformers/tokenization_utils_base.py

def convert_tokens_to_string(self, tokens: List[str]) -> str:
    """
    Converts a sequence of tokens in a single string. The most simple way to do it is `" ".join(tokens)` but we
    often want to remove sub-word tokenization artifacts at the same time.

    Args:
        tokens (`List[str]`): The token to join in a string.

    Returns:
        `str`: The joined tokens.
    """
    raise NotImplementedError

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.create_token_type_ids_from_sequences(token_ids_0, token_ids_1=None)

Create the token type IDs corresponding to the sequences passed. What are token type IDs?

Should be overridden in a subclass if the model has a special way of building those.

PARAMETER	DESCRIPTION
token_ids_0	The first tokenized sequence. TYPE: `List[int]`
token_ids_1	The second tokenized sequence. TYPE: `List[int]`, *optional* DEFAULT: None

RETURNS	DESCRIPTION
List[int]	List[int]: The token type ids.

Source code in mindnlp/transformers/tokenization_utils_base.py

def create_token_type_ids_from_sequences(
    self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
) -> List[int]:
    """
    Create the token type IDs corresponding to the sequences passed. [What are token type
    IDs?](../glossary#token-type-ids)

    Should be overridden in a subclass if the model has a special way of building those.

    Args:
        token_ids_0 (`List[int]`): The first tokenized sequence.
        token_ids_1 (`List[int]`, *optional*): The second tokenized sequence.

    Returns:
        `List[int]`: The token type ids.
    """
    if token_ids_1 is None:
        return len(token_ids_0) * [0]
    return [0] * len(token_ids_0) + [1] * len(token_ids_1)

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.decode(token_ids, skip_special_tokens=False, clean_up_tokenization_spaces=None, **kwargs)

Converts a sequence of ids in a string, using the tokenizer and vocabulary with options to remove special tokens and clean up tokenization spaces.

Similar to doing self.convert_tokens_to_string(self.convert_ids_to_tokens(token_ids)).

PARAMETER	DESCRIPTION
token_ids	List of tokenized input ids. Can be obtained using the __call__ method. TYPE: `Union[int, List[int], np.ndarray, mindspore.Tensor, tf.Tensor]`
skip_special_tokens	Whether or not to remove special tokens in the decoding. TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False
clean_up_tokenization_spaces	Whether or not to clean up the tokenization spaces. If None, will default to self.clean_up_tokenization_spaces. TYPE: `bool`, *optional* DEFAULT: None
kwargs	Will be passed to the underlying model specific decode method. TYPE: additional keyword arguments, *optional* DEFAULT: {}

RETURNS	DESCRIPTION
str	str: The decoded sentence.

Source code in mindnlp/transformers/tokenization_utils_base.py

def decode(
    self,
    token_ids: Union[int, List[int], "np.ndarray", "mindspore.Tensor"],
    skip_special_tokens: bool = False,
    clean_up_tokenization_spaces: bool = None,
    **kwargs,
) -> str:
    """
    Converts a sequence of ids in a string, using the tokenizer and vocabulary with options to remove special
    tokens and clean up tokenization spaces.

    Similar to doing `self.convert_tokens_to_string(self.convert_ids_to_tokens(token_ids))`.

    Args:
        token_ids (`Union[int, List[int], np.ndarray, mindspore.Tensor, tf.Tensor]`):
            List of tokenized input ids. Can be obtained using the `__call__` method.
        skip_special_tokens (`bool`, *optional*, defaults to `False`):
            Whether or not to remove special tokens in the decoding.
        clean_up_tokenization_spaces (`bool`, *optional*):
            Whether or not to clean up the tokenization spaces. If `None`, will default to
            `self.clean_up_tokenization_spaces`.
        kwargs (additional keyword arguments, *optional*):
            Will be passed to the underlying model specific decode method.

    Returns:
        `str`: The decoded sentence.
    """
    # Convert inputs to python lists
    token_ids = to_py_obj(token_ids)

    return self._decode(
        token_ids=token_ids,
        skip_special_tokens=skip_special_tokens,
        clean_up_tokenization_spaces=clean_up_tokenization_spaces,
        **kwargs,
    )

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.encode(text, text_pair=None, add_special_tokens=True, padding=False, truncation=None, max_length=None, stride=0, return_tensors=None, **kwargs)

Converts a string to a sequence of ids (integer), using the tokenizer and vocabulary.

Same as doing self.convert_tokens_to_ids(self.tokenize(text)).

PARAMETER	DESCRIPTION
text	The first sequence to be encoded. This can be a string, a list of strings (tokenized string using the tokenize method) or a list of integers (tokenized string ids using the convert_tokens_to_ids method). TYPE: `str`, `List[str]` or `List[int]`
text_pair	Optional second sequence to be encoded. This can be a string, a list of strings (tokenized string using the tokenize method) or a list of integers (tokenized string ids using the convert_tokens_to_ids method). TYPE: `str`, `List[str]` or `List[int]`, *optional* DEFAULT: None

Source code in mindnlp/transformers/tokenization_utils_base.py

def encode(
    self,
    text: Union[TextInput, PreTokenizedInput, EncodedInput],
    text_pair: Optional[Union[TextInput, PreTokenizedInput, EncodedInput]] = None,
    add_special_tokens: bool = True,
    padding: Union[bool, str, PaddingStrategy] = False,
    truncation: Union[bool, str, TruncationStrategy] = None,
    max_length: Optional[int] = None,
    stride: int = 0,
    return_tensors: Optional[Union[str, TensorType]] = None,
    **kwargs,
) -> List[int]:
    """
    Converts a string to a sequence of ids (integer), using the tokenizer and vocabulary.

    Same as doing `self.convert_tokens_to_ids(self.tokenize(text))`.

    Args:
        text (`str`, `List[str]` or `List[int]`):
            The first sequence to be encoded. This can be a string, a list of strings (tokenized string using the
            `tokenize` method) or a list of integers (tokenized string ids using the `convert_tokens_to_ids`
            method).
        text_pair (`str`, `List[str]` or `List[int]`, *optional*):
            Optional second sequence to be encoded. This can be a string, a list of strings (tokenized string using
            the `tokenize` method) or a list of integers (tokenized string ids using the `convert_tokens_to_ids`
            method).
    """
    encoded_inputs = self.encode_plus(
        text,
        text_pair=text_pair,
        add_special_tokens=add_special_tokens,
        padding=padding,
        truncation=truncation,
        max_length=max_length,
        stride=stride,
        return_tensors=return_tensors,
        **kwargs,
    )

    return encoded_inputs["input_ids"]

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.encode_plus(text, text_pair=None, add_special_tokens=True, padding=False, truncation=None, max_length=None, stride=0, is_split_into_words=False, pad_to_multiple_of=None, return_tensors=None, return_token_type_ids=None, return_attention_mask=None, return_overflowing_tokens=False, return_special_tokens_mask=False, return_offsets_mapping=False, return_length=False, verbose=True, **kwargs)

Tokenize and prepare for the model a sequence or a pair of sequences.

This method is deprecated, __call__ should be used instead.

PARAMETER	DESCRIPTION
text	The first sequence to be encoded. This can be a string, a list of strings (tokenized string using the tokenize method) or a list of integers (tokenized string ids using the convert_tokens_to_ids method). TYPE: `str`, `List[str]` or `List[int]` (the latter only for not-fast tokenizers
text_pair	Optional second sequence to be encoded. This can be a string, a list of strings (tokenized string using the tokenize method) or a list of integers (tokenized string ids using the convert_tokens_to_ids method). TYPE: `str`, `List[str]` or `List[int]`, *optional* DEFAULT: None

Source code in mindnlp/transformers/tokenization_utils_base.py

def encode_plus(
    self,
    text: Union[TextInput, PreTokenizedInput, EncodedInput],
    text_pair: Optional[Union[TextInput, PreTokenizedInput, EncodedInput]] = None,
    add_special_tokens: bool = True,
    padding: Union[bool, str, PaddingStrategy] = False,
    truncation: Union[bool, str, TruncationStrategy] = None,
    max_length: Optional[int] = None,
    stride: int = 0,
    is_split_into_words: bool = False,
    pad_to_multiple_of: Optional[int] = None,
    return_tensors: Optional[Union[str, TensorType]] = None,
    return_token_type_ids: Optional[bool] = None,
    return_attention_mask: Optional[bool] = None,
    return_overflowing_tokens: bool = False,
    return_special_tokens_mask: bool = False,
    return_offsets_mapping: bool = False,
    return_length: bool = False,
    verbose: bool = True,
    **kwargs,
) -> BatchEncoding:
    """
    Tokenize and prepare for the model a sequence or a pair of sequences.

    <Tip warning={true}>

    This method is deprecated, `__call__` should be used instead.

    </Tip>

    Args:
        text (`str`, `List[str]` or `List[int]` (the latter only for not-fast tokenizers)):
            The first sequence to be encoded. This can be a string, a list of strings (tokenized string using the
            `tokenize` method) or a list of integers (tokenized string ids using the `convert_tokens_to_ids`
            method).
        text_pair (`str`, `List[str]` or `List[int]`, *optional*):
            Optional second sequence to be encoded. This can be a string, a list of strings (tokenized string using
            the `tokenize` method) or a list of integers (tokenized string ids using the `convert_tokens_to_ids`
            method).
    """
    # Backward compatibility for 'truncation_strategy', 'pad_to_max_length'
    padding_strategy, truncation_strategy, max_length, kwargs = self._get_padding_truncation_strategies(
        padding=padding,
        truncation=truncation,
        max_length=max_length,
        pad_to_multiple_of=pad_to_multiple_of,
        verbose=verbose,
        **kwargs,
    )

    return self._encode_plus(
        text=text,
        text_pair=text_pair,
        add_special_tokens=add_special_tokens,
        padding_strategy=padding_strategy,
        truncation_strategy=truncation_strategy,
        max_length=max_length,
        stride=stride,
        is_split_into_words=is_split_into_words,
        pad_to_multiple_of=pad_to_multiple_of,
        return_tensors=return_tensors,
        return_token_type_ids=return_token_type_ids,
        return_attention_mask=return_attention_mask,
        return_overflowing_tokens=return_overflowing_tokens,
        return_special_tokens_mask=return_special_tokens_mask,
        return_offsets_mapping=return_offsets_mapping,
        return_length=return_length,
        verbose=verbose,
        **kwargs,
    )

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.from_pretrained(pretrained_model_name_or_path, *init_inputs, cache_dir=None, force_download=False, local_files_only=False, token=None, mirror='huggingface', **kwargs) classmethod

Instantiate a [~tokenization_utils_base.PreTrainedTokenizerBase] (or a derived class) from a predefined tokenizer.

PARAMETER	DESCRIPTION
pretrained_model_name_or_path	Can be either: A string, the model id of a predefined tokenizer hosted inside a model repo on hf-mirror.com. Valid model ids can be located at the root-level, like bert-base-uncased, or namespaced under a user or organization name, like dbmdz/bert-base-german-cased. A path to a directory containing vocabulary files required by the tokenizer, for instance saved using the [~tokenization_utils_base.PreTrainedTokenizerBase.save_pretrained] method, e.g., ./my_model_directory/. (Deprecated, not applicable to all derived classes) A path or url to a single saved vocabulary file (if and only if the tokenizer only requires a single vocabulary file like Bert or XLNet), e.g., ./my_model_directory/vocab.txt. TYPE: `str` or `os.PathLike`
cache_dir	Path to a directory in which a downloaded predefined tokenizer vocabulary files should be cached if the standard cache should not be used. TYPE: `str` or `os.PathLike`, *optional* DEFAULT: None
force_download	Whether or not to force the (re-)download the vocabulary files and override the cached versions if they exist. TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False
resume_download	Whether or not to delete incompletely received files. Attempt to resume the download if such a file exists. TYPE: `bool`, *optional*, defaults to `False`
proxies	A dictionary of proxy servers to use by protocol or endpoint, e.g., {'http': 'foo.bar:3128', 'http://hostname': 'foo.bar:4012'}. The proxies are used on each request. TYPE: `Dict[str, str]`, *optional*
token	The token to use as HTTP bearer authorization for remote files. If True, will use the token generated when running huggingface-cli login (stored in ~/.huggingface). TYPE: `str` or *bool*, *optional* DEFAULT: None
local_files_only	Whether or not to only rely on local files and not to attempt to download any files. TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False
revision	The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a git-based system for storing models and other artifacts on hf-mirror.com, so revision can be any identifier allowed by git. TYPE: `str`, *optional*, defaults to `"main"`
subfolder	In case the relevant files are located inside a subfolder of the model repo on hf-mirror.com (e.g. for facebook/rag-token-base), specify it here. TYPE: `str`, *optional*
inputs	Will be passed along to the Tokenizer __init__ method. TYPE: additional positional arguments, *optional*
kwargs	Will be passed to the Tokenizer __init__ method. Can be used to set special tokens like bos_token, eos_token, unk_token, sep_token, pad_token, cls_token, mask_token, additional_special_tokens. See parameters in the __init__ for more details. TYPE: additional keyword arguments, *optional* DEFAULT: {}

Passing token=True is required when you want to use a private model.

Example

>>> # We can't instantiate directly the base class *PreTrainedTokenizerBase* so let's show our examples on a derived class: BertTokenizer
>>> # Download vocabulary from hf-mirror.com and cache.
>>> tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
...
>>> # Download vocabulary from hf-mirror.com (user-uploaded) and cache.
>>> tokenizer = BertTokenizer.from_pretrained("dbmdz/bert-base-german-cased")
...
>>> # If vocabulary files are in a directory (e.g. tokenizer was saved using *save_pretrained('./test/saved_model/')*)
>>> tokenizer = BertTokenizer.from_pretrained("./test/saved_model/")
...
>>> # If the tokenizer uses a single vocabulary file, you can point directly to this file
>>> tokenizer = BertTokenizer.from_pretrained("./test/saved_model/my_vocab.txt")
...
>>> # You can link tokens to special vocabulary when instantiating
>>> tokenizer = BertTokenizer.from_pretrained("bert-base-uncased", unk_token="<unk>")
>>> # You should be sure '<unk>' is in the vocabulary when doing that.
>>> # Otherwise use tokenizer.add_special_tokens({'unk_token': '<unk>'}) instead)
>>> assert tokenizer.unk_token == "<unk>"

Source code in mindnlp/transformers/tokenization_utils_base.py

@classmethod
def from_pretrained(
    cls,
    pretrained_model_name_or_path: Union[str, os.PathLike],
    *init_inputs,
    cache_dir: Optional[Union[str, os.PathLike]] = None,
    force_download: bool = False,
    local_files_only: bool = False,
    token: str = None,
    mirror: str = 'huggingface',
    **kwargs,
):
    r"""
    Instantiate a [`~tokenization_utils_base.PreTrainedTokenizerBase`] (or a derived class) from a predefined
    tokenizer.

    Args:
        pretrained_model_name_or_path (`str` or `os.PathLike`):
            Can be either:

            - A string, the *model id* of a predefined tokenizer hosted inside a model repo on hf-mirror.com.
              Valid model ids can be located at the root-level, like `bert-base-uncased`, or namespaced under a
              user or organization name, like `dbmdz/bert-base-german-cased`.
            - A path to a *directory* containing vocabulary files required by the tokenizer, for instance saved
              using the [`~tokenization_utils_base.PreTrainedTokenizerBase.save_pretrained`] method, e.g.,
              `./my_model_directory/`.
            - (**Deprecated**, not applicable to all derived classes) A path or url to a single saved vocabulary
              file (if and only if the tokenizer only requires a single vocabulary file like Bert or XLNet), e.g.,
              `./my_model_directory/vocab.txt`.
        cache_dir (`str` or `os.PathLike`, *optional*):
            Path to a directory in which a downloaded predefined tokenizer vocabulary files should be cached if the
            standard cache should not be used.
        force_download (`bool`, *optional*, defaults to `False`):
            Whether or not to force the (re-)download the vocabulary files and override the cached versions if they
            exist.
        resume_download (`bool`, *optional*, defaults to `False`):
            Whether or not to delete incompletely received files. Attempt to resume the download if such a file
            exists.
        proxies (`Dict[str, str]`, *optional*):
            A dictionary of proxy servers to use by protocol or endpoint, e.g., `{'http': 'foo.bar:3128',
            'http://hostname': 'foo.bar:4012'}`. The proxies are used on each request.
        token (`str` or *bool*, *optional*):
            The token to use as HTTP bearer authorization for remote files. If `True`, will use the token generated
            when running `huggingface-cli login` (stored in `~/.huggingface`).
        local_files_only (`bool`, *optional*, defaults to `False`):
            Whether or not to only rely on local files and not to attempt to download any files.
        revision (`str`, *optional*, defaults to `"main"`):
            The specific model version to use. It can be a branch name, a tag name, or a commit id, since we use a
            git-based system for storing models and other artifacts on hf-mirror.com, so `revision` can be any
            identifier allowed by git.
        subfolder (`str`, *optional*):
            In case the relevant files are located inside a subfolder of the model repo on hf-mirror.com (e.g. for
            facebook/rag-token-base), specify it here.
        inputs (additional positional arguments, *optional*):
            Will be passed along to the Tokenizer `__init__` method.
        kwargs (additional keyword arguments, *optional*):
            Will be passed to the Tokenizer `__init__` method. Can be used to set special tokens like `bos_token`,
            `eos_token`, `unk_token`, `sep_token`, `pad_token`, `cls_token`, `mask_token`,
            `additional_special_tokens`. See parameters in the `__init__` for more details.

    <Tip>

    Passing `token=True` is required when you want to use a private model.

    </Tip>

    Example:
        ```python
        >>> # We can't instantiate directly the base class *PreTrainedTokenizerBase* so let's show our examples on a derived class: BertTokenizer
        >>> # Download vocabulary from hf-mirror.com and cache.
        >>> tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
        ...
        >>> # Download vocabulary from hf-mirror.com (user-uploaded) and cache.
        >>> tokenizer = BertTokenizer.from_pretrained("dbmdz/bert-base-german-cased")
        ...
        >>> # If vocabulary files are in a directory (e.g. tokenizer was saved using *save_pretrained('./test/saved_model/')*)
        >>> tokenizer = BertTokenizer.from_pretrained("./test/saved_model/")
        ...
        >>> # If the tokenizer uses a single vocabulary file, you can point directly to this file
        >>> tokenizer = BertTokenizer.from_pretrained("./test/saved_model/my_vocab.txt")
        ...
        >>> # You can link tokens to special vocabulary when instantiating
        >>> tokenizer = BertTokenizer.from_pretrained("bert-base-uncased", unk_token="<unk>")
        >>> # You should be sure '<unk>' is in the vocabulary when doing that.
        >>> # Otherwise use tokenizer.add_special_tokens({'unk_token': '<unk>'}) instead)
        >>> assert tokenizer.unk_token == "<unk>"
        ```
    """
    resume_download = kwargs.pop("resume_download", False)
    proxies = kwargs.pop("proxies", None)
    subfolder = kwargs.pop("subfolder", None)
    revision = kwargs.pop("revision", "main")

    if is_offline_mode() and not local_files_only:
        logger.info("Offline mode: forcing local_files_only=True")
        local_files_only = True

    pretrained_model_name_or_path = str(pretrained_model_name_or_path)
    vocab_files = {}
    init_configuration = {}

    is_local = os.path.isdir(pretrained_model_name_or_path)
    single_file_id = None
    if os.path.isfile(pretrained_model_name_or_path) or is_remote_url(pretrained_model_name_or_path):
        if len(cls.vocab_files_names) > 1:
            raise ValueError(
                f"Calling {cls.__name__}.from_pretrained() with the path to a single file or url is not "
                "supported for this tokenizer. Use a model identifier or the path to a directory instead."
            )
        warnings.warn(
            f"Calling {cls.__name__}.from_pretrained() with the path to a single file or url is deprecated and "
            "won't be possible anymore in v5. Use a model identifier or the path to a directory instead.",
            FutureWarning,
        )
        file_id = list(cls.vocab_files_names.keys())[0]

        vocab_files[file_id] = pretrained_model_name_or_path
        single_file_id = file_id
    else:
        # At this point pretrained_model_name_or_path is either a directory or a model identifier name
        additional_files_names = {
            "added_tokens_file": ADDED_TOKENS_FILE,  # kept only for legacy
            "special_tokens_map_file": SPECIAL_TOKENS_MAP_FILE,  # kept only for legacy
            "tokenizer_config_file": TOKENIZER_CONFIG_FILE,
            # tokenizer_file used to initialize a slow from a fast. Properly copy the `addedTokens` instead of adding in random orders
            "tokenizer_file": FULL_TOKENIZER_FILE,
        }
        vocab_files = {**cls.vocab_files_names, **additional_files_names}
        if "tokenizer_file" in vocab_files:
            # Try to get the tokenizer config to see if there are versioned tokenizer files.
            fast_tokenizer_file = FULL_TOKENIZER_FILE
            resolved_config_file = cached_file(
                pretrained_model_name_or_path,
                TOKENIZER_CONFIG_FILE,
                cache_dir=cache_dir,
                force_download=force_download,
                resume_download=resume_download,
                proxies=proxies,
                local_files_only=local_files_only,
                token=token,
                subfolder=subfolder,
                revision=revision,
                mirror=mirror,
                _raise_exceptions_for_missing_entries=False,
                _raise_exceptions_for_connection_errors=False,
            )
            if resolved_config_file is not None:
                with open(resolved_config_file, encoding="utf-8") as reader:
                    tokenizer_config = json.load(reader)
                    if "fast_tokenizer_files" in tokenizer_config:
                        fast_tokenizer_file = get_fast_tokenizer_file(tokenizer_config["fast_tokenizer_files"])
            vocab_files["tokenizer_file"] = fast_tokenizer_file

    # Get files from url, cache, or disk depending on the case
    resolved_vocab_files = {}
    unresolved_files = []
    for file_id, file_path in vocab_files.items():
        if file_path is None:
            resolved_vocab_files[file_id] = None
        elif single_file_id == file_id:
            if os.path.isfile(file_path):
                resolved_vocab_files[file_id] = file_path
            elif is_remote_url(file_path):
                resolved_vocab_files[file_id] = download_url(file_path, proxies=proxies)
        else:
            resolved_vocab_files[file_id] = cached_file(
                pretrained_model_name_or_path,
                file_path,
                cache_dir=cache_dir,
                force_download=force_download,
                proxies=proxies,
                resume_download=resume_download,
                local_files_only=local_files_only,
                token=token,
                subfolder=subfolder,
                revision=revision,
                mirror=mirror,
                _raise_exceptions_for_missing_entries=False,
                _raise_exceptions_for_connection_errors=False,
            )
    if len(unresolved_files) > 0:
        logger.info(
            f"Can't load following files from cache: {unresolved_files} and cannot check if these "
            "files are necessary for the tokenizer to operate."
        )

    if all(full_file_name is None for full_file_name in resolved_vocab_files.values()):
        raise EnvironmentError(
            f"Can't load tokenizer for '{pretrained_model_name_or_path}'. If you were trying to load it from "
            "'https://hf-mirror.com/models', make sure you don't have a local directory with the same name. "
            f"Otherwise, make sure '{pretrained_model_name_or_path}' is the correct path to a directory "
            f"containing all relevant files for a {cls.__name__} tokenizer."
        )

    for file_id, file_path in vocab_files.items():
        if file_id not in resolved_vocab_files:
            continue

        if is_local:
            logger.info(f"loading file {file_path}")
        else:
            logger.info(f"loading file {file_path} from cache at {resolved_vocab_files[file_id]}")

    return cls._from_pretrained(
        resolved_vocab_files,
        pretrained_model_name_or_path,
        init_configuration,
        *init_inputs,
        cache_dir=cache_dir,
        local_files_only=local_files_only,
        _is_local=is_local,
        **kwargs,
    )

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.get_special_tokens_mask(token_ids_0, token_ids_1=None, already_has_special_tokens=False)

Retrieves sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the tokenizer prepare_for_model or encode_plus methods.

PARAMETER	DESCRIPTION
token_ids_0	List of ids of the first sequence. TYPE: `List[int]`
token_ids_1	List of ids of the second sequence. TYPE: `List[int]`, *optional* DEFAULT: None
already_has_special_tokens	Whether or not the token list is already formatted with special tokens for the model. TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False

RETURNS	DESCRIPTION
List[int]	A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.

Source code in mindnlp/transformers/tokenization_utils_base.py

def get_special_tokens_mask(
    self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
) -> List[int]:
    """
    Retrieves sequence ids from a token list that has no special tokens added. This method is called when adding
    special tokens using the tokenizer `prepare_for_model` or `encode_plus` methods.

    Args:
        token_ids_0 (`List[int]`):
            List of ids of the first sequence.
        token_ids_1 (`List[int]`, *optional*):
            List of ids of the second sequence.
        already_has_special_tokens (`bool`, *optional*, defaults to `False`):
            Whether or not the token list is already formatted with special tokens for the model.

    Returns:
        A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
    """
    assert already_has_special_tokens and token_ids_1 is None, (
        "You cannot use ``already_has_special_tokens=False`` with this tokenizer. "
        "Please use a slow (full python) tokenizer to activate this argument. "
        "Or set `return_special_tokens_mask=True` when calling the encoding method "
        "to get the special tokens mask in any tokenizer. "
    )

    all_special_ids = self.all_special_ids  # cache the property

    special_tokens_mask = [1 if token in all_special_ids else 0 for token in token_ids_0]

    return special_tokens_mask

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.get_vocab()

Returns the vocabulary as a dictionary of token to index.

tokenizer.get_vocab()[token] is equivalent to tokenizer.convert_tokens_to_ids(token) when token is in the vocab.

RETURNS	DESCRIPTION
Dict[str, int]	Dict[str, int]: The vocabulary.

Source code in mindnlp/transformers/tokenization_utils_base.py

def get_vocab(self) -> Dict[str, int]:
    """
    Returns the vocabulary as a dictionary of token to index.

    `tokenizer.get_vocab()[token]` is equivalent to `tokenizer.convert_tokens_to_ids(token)` when `token` is in the
    vocab.

    Returns:
        `Dict[str, int]`: The vocabulary.
    """
    raise NotImplementedError()

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.num_special_tokens_to_add(pair=False)

num_special_tokens_to_add method in the PreTrainedTokenizerBase class calculates the number of special tokens to be added.

PARAMETER	DESCRIPTION
self	An instance of the PreTrainedTokenizerBase class.
pair	A boolean flag indicating whether the tokens are paired. Defaults to False. TYPE: bool DEFAULT: False

RETURNS	DESCRIPTION
int	The number of special tokens to be added based on the input parameters. TYPE: int

RAISES	DESCRIPTION
NotImplementedError	If the method is called directly from the base class without being implemented in the derived class.

Source code in mindnlp/transformers/tokenization_utils_base.py

def num_special_tokens_to_add(self, pair: bool = False) -> int:
    r"""
    num_special_tokens_to_add method in the PreTrainedTokenizerBase class calculates the number of special tokens to be added.

    Args:
        self: An instance of the PreTrainedTokenizerBase class.
        pair (bool): A boolean flag indicating whether the tokens are paired. Defaults to False.

    Returns:
        int: The number of special tokens to be added based on the input parameters.

    Raises:
        NotImplementedError: If the method is called directly from the base class without being implemented in the derived class.
    """
    raise NotImplementedError

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.pad(encoded_inputs, padding=True, max_length=None, pad_to_multiple_of=None, return_attention_mask=None, return_tensors=None, verbose=True)

Pad a single encoded input or a batch of encoded inputs up to predefined length or to the max sequence length in the batch.

Padding side (left/right) padding token ids are defined at the tokenizer level (with self.padding_side, self.pad_token_id and self.pad_token_type_id).

Please note that with a fast tokenizer, using the __call__ method is faster than using a method to encode the text followed by a call to the pad method to get a padded encoding.

If the encoded_inputs passed are dictionary of numpy arrays, PyTorch tensors or TensorFlow tensors, the result will use the same type unless you provide a different tensor type with return_tensors. In the case of PyTorch tensors, you will lose the specific device of your tensors however.

PARAMETER	DESCRIPTION
encoded_inputs	Tokenized inputs. Can represent one input ([BatchEncoding] or Dict[str, List[int]]) or a batch of tokenized inputs (list of [BatchEncoding], Dict[str, List[List[int]]] or List[Dict[str, List[int]]]) so you can use this method during preprocessing as well as in a PyTorch Dataloader collate function. Instead of List[int] you can have tensors (numpy arrays, PyTorch tensors or TensorFlow tensors), see the note above for the return type. TYPE: [`BatchEncoding`], list of [`BatchEncoding`], `Dict[str, List[int]]`, `Dict[str, List[List[int]]` or `List[Dict[str, List[int]]]`
padding	Select a strategy to pad the returned sequences (according to the model's padding side and padding index) among: True or 'longest': Pad to the longest sequence in the batch (or no padding if only a single sequence if provided). 'max_length': Pad to a maximum length specified with the argument max_length or to the maximum acceptable input length for the model if that argument is not provided. False or 'do_not_pad' (default): No padding (i.e., can output a batch with sequences of different lengths). TYPE: `bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `True` DEFAULT: True
max_length	Maximum length of the returned list and optionally padding length (see above). TYPE: `int`, *optional* DEFAULT: None
pad_to_multiple_of	If set will pad the sequence to a multiple of the provided value. This is especially useful to enable the use of Tensor Cores on NVIDIA hardware with compute capability >= 7.5 (Volta). TYPE: `int`, *optional* DEFAULT: None
return_attention_mask	Whether to return the attention mask. If left to the default, will return the attention mask according to the specific tokenizer's default, defined by the return_outputs attribute. What are attention masks? TYPE: `bool`, *optional* DEFAULT: None
return_tensors	If set, will return tensors instead of list of python integers. Acceptable values are: 'tf': Return TensorFlow tf.constant objects. 'pt': Return PyTorch mindspore.Tensor objects. 'np': Return Numpy np.ndarray objects. TYPE: `str` or [`~utils.TensorType`], *optional* DEFAULT: None
verbose	Whether or not to print more information and warnings. TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True

Source code in mindnlp/transformers/tokenization_utils_base.py

def pad(
    self,
    encoded_inputs: Union[
        BatchEncoding,
        List[BatchEncoding],
        Dict[str, EncodedInput],
        Dict[str, List[EncodedInput]],
        List[Dict[str, EncodedInput]],
    ],
    padding: Union[bool, str, PaddingStrategy] = True,
    max_length: Optional[int] = None,
    pad_to_multiple_of: Optional[int] = None,
    return_attention_mask: Optional[bool] = None,
    return_tensors: Optional[Union[str, TensorType]] = None,
    verbose: bool = True,
) -> BatchEncoding:
    """
    Pad a single encoded input or a batch of encoded inputs up to predefined length or to the max sequence length
    in the batch.

    Padding side (left/right) padding token ids are defined at the tokenizer level (with `self.padding_side`,
    `self.pad_token_id` and `self.pad_token_type_id`).

    Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the
    text followed by a call to the `pad` method to get a padded encoding.

    <Tip>

    If the `encoded_inputs` passed are dictionary of numpy arrays, PyTorch tensors or TensorFlow tensors, the
    result will use the same type unless you provide a different tensor type with `return_tensors`. In the case of
    PyTorch tensors, you will lose the specific device of your tensors however.

    </Tip>

    Args:
        encoded_inputs ([`BatchEncoding`], list of [`BatchEncoding`], `Dict[str, List[int]]`, `Dict[str, List[List[int]]` or `List[Dict[str, List[int]]]`):
            Tokenized inputs. Can represent one input ([`BatchEncoding`] or `Dict[str, List[int]]`) or a batch of
            tokenized inputs (list of [`BatchEncoding`], *Dict[str, List[List[int]]]* or *List[Dict[str,
            List[int]]]*) so you can use this method during preprocessing as well as in a PyTorch Dataloader
            collate function.

            Instead of `List[int]` you can have tensors (numpy arrays, PyTorch tensors or TensorFlow tensors), see
            the note above for the return type.
        padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `True`):
             Select a strategy to pad the returned sequences (according to the model's padding side and padding
             index) among:

            - `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single
              sequence if provided).
            - `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum
              acceptable input length for the model if that argument is not provided.
            - `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different
              lengths).
        max_length (`int`, *optional*):
            Maximum length of the returned list and optionally padding length (see above).
        pad_to_multiple_of (`int`, *optional*):
            If set will pad the sequence to a multiple of the provided value.

            This is especially useful to enable the use of Tensor Cores on NVIDIA hardware with compute capability
            `>= 7.5` (Volta).
        return_attention_mask (`bool`, *optional*):
            Whether to return the attention mask. If left to the default, will return the attention mask according
            to the specific tokenizer's default, defined by the `return_outputs` attribute.

            [What are attention masks?](../glossary#attention-mask)
        return_tensors (`str` or [`~utils.TensorType`], *optional*):
            If set, will return tensors instead of list of python integers. Acceptable values are:

            - `'tf'`: Return TensorFlow `tf.constant` objects.
            - `'pt'`: Return PyTorch `mindspore.Tensor` objects.
            - `'np'`: Return Numpy `np.ndarray` objects.
        verbose (`bool`, *optional*, defaults to `True`):
            Whether or not to print more information and warnings.
    """
    if self.__class__.__name__.endswith("Fast"):
        if not self.deprecation_warnings.get("Asking-to-pad-a-fast-tokenizer", False):
            logger.warning_advice(
                f"You're using a {self.__class__.__name__} tokenizer. Please note that with a fast tokenizer,"
                " using the `__call__` method is faster than using a method to encode the text followed by a call"
                " to the `pad` method to get a padded encoding."
            )
            self.deprecation_warnings["Asking-to-pad-a-fast-tokenizer"] = True

    # If we have a list of dicts, let's convert it in a dict of lists
    # We do this to allow using this method as a collate_fn function in PyTorch Dataloader
    if isinstance(encoded_inputs, (list, tuple)) and isinstance(encoded_inputs[0], Mapping):
        encoded_inputs = {key: [example[key] for example in encoded_inputs] for key in encoded_inputs[0].keys()}

    # The model's main input name, usually `input_ids`, has be passed for padding
    if self.model_input_names[0] not in encoded_inputs:
        raise ValueError(
            "You should supply an encoding or a list of encodings to this method "
            f"that includes {self.model_input_names[0]}, but you provided {list(encoded_inputs.keys())}"
        )

    required_input = encoded_inputs[self.model_input_names[0]]

    if required_input is None or (isinstance(required_input, Sized) and len(required_input) == 0):
        if return_attention_mask:
            encoded_inputs["attention_mask"] = []
        return encoded_inputs

    # If we have PyTorch/TF/NumPy tensors/arrays as inputs, we cast them as python objects
    # and rebuild them afterwards if no return_tensors is specified
    # Note that we lose the specific device the tensor may be on for PyTorch

    first_element = required_input[0]
    if isinstance(first_element, (list, tuple)):
        # first_element might be an empty list/tuple in some edge cases so we grab the first non empty element.
        for item in required_input:
            if len(item) != 0:
                first_element = item[0]
                break
    # At this state, if `first_element` is still a list/tuple, it's an empty one so there is nothing to do.
    if not isinstance(first_element, (int, list, tuple)):
        if isinstance(first_element, mindspore.Tensor):
            return_tensors = "ms" if return_tensors is None else return_tensors
        elif isinstance(first_element, np.ndarray):
            return_tensors = "np" if return_tensors is None else return_tensors
        else:
            raise ValueError(
                f"type of {first_element} unknown: {type(first_element)}. "
                "Should be one of a python, numpy, pytorch or tensorflow object."
            )

        for key, value in encoded_inputs.items():
            encoded_inputs[key] = to_py_obj(value)

    # Convert padding_strategy in PaddingStrategy
    padding_strategy, _, max_length, _ = self._get_padding_truncation_strategies(
        padding=padding, max_length=max_length, verbose=verbose
    )

    required_input = encoded_inputs[self.model_input_names[0]]
    if required_input and not isinstance(required_input[0], (list, tuple)):
        encoded_inputs = self._pad(
            encoded_inputs,
            max_length=max_length,
            padding_strategy=padding_strategy,
            pad_to_multiple_of=pad_to_multiple_of,
            return_attention_mask=return_attention_mask,
        )
        return BatchEncoding(encoded_inputs, tensor_type=return_tensors)

    batch_size = len(required_input)
    assert all(
        len(v) == batch_size for v in encoded_inputs.values()
    ), "Some items in the output dictionary have a different batch size than others."

    if padding_strategy == PaddingStrategy.LONGEST:
        max_length = max(len(inputs) for inputs in required_input)
        padding_strategy = PaddingStrategy.MAX_LENGTH

    batch_outputs = {}
    for i in range(batch_size):
        inputs = {k: v[i] for k, v in encoded_inputs.items()}
        outputs = self._pad(
            inputs,
            max_length=max_length,
            padding_strategy=padding_strategy,
            pad_to_multiple_of=pad_to_multiple_of,
            return_attention_mask=return_attention_mask,
        )

        for key, value in outputs.items():
            if key not in batch_outputs:
                batch_outputs[key] = []
            batch_outputs[key].append(value)

    return BatchEncoding(batch_outputs, tensor_type=return_tensors)

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.prepare_for_model(ids, pair_ids=None, add_special_tokens=True, padding=False, truncation=None, max_length=None, stride=0, pad_to_multiple_of=None, return_tensors=None, return_token_type_ids=None, return_attention_mask=None, return_overflowing_tokens=False, return_special_tokens_mask=False, return_offsets_mapping=False, return_length=False, verbose=True, prepend_batch_axis=False, **kwargs)

Prepares a sequence of input id, or a pair of sequences of inputs ids so that it can be used by the model. It adds special tokens, truncates sequences if overflowing while taking into account the special tokens and manages a moving window (with user defined stride) for overflowing tokens. Please Note, for pair_ids different than None and truncation_strategy = longest_first or True, it is not possible to return overflowing tokens. Such a combination of arguments will raise an error.

PARAMETER	DESCRIPTION
ids	Tokenized input ids of the first sequence. Can be obtained from a string by chaining the tokenize and convert_tokens_to_ids methods. TYPE: `List[int]`
pair_ids	Tokenized input ids of the second sequence. Can be obtained from a string by chaining the tokenize and convert_tokens_to_ids methods. TYPE: `List[int]`, *optional* DEFAULT: None

Source code in mindnlp/transformers/tokenization_utils_base.py

def prepare_for_model(
    self,
    ids: List[int],
    pair_ids: Optional[List[int]] = None,
    add_special_tokens: bool = True,
    padding: Union[bool, str, PaddingStrategy] = False,
    truncation: Union[bool, str, TruncationStrategy] = None,
    max_length: Optional[int] = None,
    stride: int = 0,
    pad_to_multiple_of: Optional[int] = None,
    return_tensors: Optional[Union[str, TensorType]] = None,
    return_token_type_ids: Optional[bool] = None,
    return_attention_mask: Optional[bool] = None,
    return_overflowing_tokens: bool = False,
    return_special_tokens_mask: bool = False,
    return_offsets_mapping: bool = False,
    return_length: bool = False,
    verbose: bool = True,
    prepend_batch_axis: bool = False,
    **kwargs,
) -> BatchEncoding:
    """
    Prepares a sequence of input id, or a pair of sequences of inputs ids so that it can be used by the model. It
    adds special tokens, truncates sequences if overflowing while taking into account the special tokens and
    manages a moving window (with user defined stride) for overflowing tokens. Please Note, for *pair_ids*
    different than `None` and *truncation_strategy = longest_first* or `True`, it is not possible to return
    overflowing tokens. Such a combination of arguments will raise an error.

    Args:
        ids (`List[int]`):
            Tokenized input ids of the first sequence. Can be obtained from a string by chaining the `tokenize` and
            `convert_tokens_to_ids` methods.
        pair_ids (`List[int]`, *optional*):
            Tokenized input ids of the second sequence. Can be obtained from a string by chaining the `tokenize`
            and `convert_tokens_to_ids` methods.
    """
    # Backward compatibility for 'truncation_strategy', 'pad_to_max_length'
    padding_strategy, truncation_strategy, max_length, kwargs = self._get_padding_truncation_strategies(
        padding=padding,
        truncation=truncation,
        max_length=max_length,
        pad_to_multiple_of=pad_to_multiple_of,
        verbose=verbose,
        **kwargs,
    )

    pair = bool(pair_ids is not None)
    len_ids = len(ids)
    len_pair_ids = len(pair_ids) if pair else 0

    if return_token_type_ids and not add_special_tokens:
        raise ValueError(
            "Asking to return token_type_ids while setting add_special_tokens to False "
            "results in an undefined behavior. Please set add_special_tokens to True or "
            "set return_token_type_ids to None."
        )

    if (
        return_overflowing_tokens
        and truncation_strategy == TruncationStrategy.LONGEST_FIRST
        and pair_ids is not None
    ):
        raise ValueError(
            "Not possible to return overflowing tokens for pair of sequences with the "
            "`longest_first`. Please select another truncation strategy than `longest_first`, "
            "for instance `only_second` or `only_first`."
        )

    # Load from model defaults
    if return_token_type_ids is None:
        return_token_type_ids = "token_type_ids" in self.model_input_names
    if return_attention_mask is None:
        return_attention_mask = "attention_mask" in self.model_input_names

    encoded_inputs = {}

    # Compute the total size of the returned encodings
    total_len = len_ids + len_pair_ids + (self.num_special_tokens_to_add(pair=pair) if add_special_tokens else 0)

    # Truncation: Handle max sequence length
    overflowing_tokens = []
    if truncation_strategy != TruncationStrategy.DO_NOT_TRUNCATE and max_length and total_len > max_length:
        ids, pair_ids, overflowing_tokens = self.truncate_sequences(
            ids,
            pair_ids=pair_ids,
            num_tokens_to_remove=total_len - max_length,
            truncation_strategy=truncation_strategy,
            stride=stride,
        )

    if return_overflowing_tokens:
        encoded_inputs["overflowing_tokens"] = overflowing_tokens
        encoded_inputs["num_truncated_tokens"] = total_len - max_length

    # Add special tokens
    if add_special_tokens:
        sequence = self.build_inputs_with_special_tokens(ids, pair_ids)
        token_type_ids = self.create_token_type_ids_from_sequences(ids, pair_ids)
    else:
        sequence = ids + pair_ids if pair else ids
        token_type_ids = [0] * len(ids) + ([0] * len(pair_ids) if pair else [])

    # Build output dictionary
    encoded_inputs["input_ids"] = sequence
    if return_token_type_ids:
        encoded_inputs["token_type_ids"] = token_type_ids
    if return_special_tokens_mask:
        if add_special_tokens:
            encoded_inputs["special_tokens_mask"] = self.get_special_tokens_mask(ids, pair_ids)
        else:
            encoded_inputs["special_tokens_mask"] = [0] * len(sequence)

    # Check lengths
    self._eventual_warn_about_too_long_sequence(encoded_inputs["input_ids"], max_length, verbose)

    # Padding
    if padding_strategy != PaddingStrategy.DO_NOT_PAD or return_attention_mask:
        encoded_inputs = self.pad(
            encoded_inputs,
            max_length=max_length,
            padding=padding_strategy.value,
            pad_to_multiple_of=pad_to_multiple_of,
            return_attention_mask=return_attention_mask,
        )

    if return_length:
        encoded_inputs["length"] = len(encoded_inputs["input_ids"])

    batch_outputs = BatchEncoding(
        encoded_inputs, tensor_type=return_tensors, prepend_batch_axis=prepend_batch_axis
    )

    return batch_outputs

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.prepare_seq2seq_batch(src_texts, tgt_texts=None, max_length=None, max_target_length=None, padding='longest', return_tensors=None, truncation=True, **kwargs)

Prepare model inputs for translation. For best performance, translate one sentence at a time.

PARAMETER	DESCRIPTION
src_texts	List of documents to summarize or source language texts. TYPE: `List[str]`
tgt_texts	List of summaries or target language texts. TYPE: `list`, *optional* DEFAULT: None
max_length	Controls the maximum length for encoder inputs (documents to summarize or source language texts) If left unset or set to None, this will use the predefined model maximum length if a maximum length is required by one of the truncation/padding parameters. If the model has no specific maximum input length (like XLNet) truncation/padding to a maximum length will be deactivated. TYPE: `int`, *optional* DEFAULT: None
max_target_length	Controls the maximum length of decoder inputs (target language texts or summaries) If left unset or set to None, this will use the max_length value. TYPE: `int`, *optional* DEFAULT: None
padding	Activates and controls padding. Accepts the following values: True or 'longest': Pad to the longest sequence in the batch (or no padding if only a single sequence if provided). 'max_length': Pad to a maximum length specified with the argument max_length or to the maximum acceptable input length for the model if that argument is not provided. False or 'do_not_pad' (default): No padding (i.e., can output a batch with sequences of different lengths). TYPE: `bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `False` DEFAULT: 'longest'
return_tensors	If set, will return tensors instead of list of python integers. Acceptable values are: 'tf': Return TensorFlow tf.constant objects. 'pt': Return PyTorch mindspore.Tensor objects. 'np': Return Numpy np.ndarray objects. TYPE: `str` or [`~utils.TensorType`], *optional* DEFAULT: None
truncation	Activates and controls truncation. Accepts the following values: True or 'longest_first': Truncate to a maximum length specified with the argument max_length or to the maximum acceptable input length for the model if that argument is not provided. This will truncate token by token, removing a token from the longest sequence in the pair if a pair of sequences (or a batch of pairs) is provided. 'only_first': Truncate to a maximum length specified with the argument max_length or to the maximum acceptable input length for the model if that argument is not provided. This will only truncate the first sequence of a pair if a pair of sequences (or a batch of pairs) is provided. 'only_second': Truncate to a maximum length specified with the argument max_length or to the maximum acceptable input length for the model if that argument is not provided. This will only truncate the second sequence of a pair if a pair of sequences (or a batch of pairs) is provided. False or 'do_not_truncate' (default): No truncation (i.e., can output batch with sequence lengths greater than the model maximum admissible input size). TYPE: `bool`, `str` or [`~tokenization_utils_base.TruncationStrategy`], *optional*, defaults to `True` DEFAULT: True
**kwargs	Additional keyword arguments passed along to self.__call__. DEFAULT: {}

RETURNS	DESCRIPTION
BatchEncoding	[BatchEncoding]: A [BatchEncoding] with the following fields:
BatchEncoding	input_ids -- List of token ids to be fed to the encoder.
BatchEncoding	attention_mask -- List of indices specifying which tokens should be attended to by the model.
BatchEncoding	labels -- List of token ids for tgt_texts.
BatchEncoding	The full set of keys [input_ids, attention_mask, labels], will only be returned if tgt_texts is passed.
BatchEncoding	Otherwise, input_ids, attention_mask will be the only keys.

Source code in mindnlp/transformers/tokenization_utils_base.py

    def prepare_seq2seq_batch(
        self,
        src_texts: List[str],
        tgt_texts: Optional[List[str]] = None,
        max_length: Optional[int] = None,
        max_target_length: Optional[int] = None,
        padding: str = "longest",
        return_tensors: str = None,
        truncation: bool = True,
        **kwargs,
    ) -> BatchEncoding:
        """
        Prepare model inputs for translation. For best performance, translate one sentence at a time.

        Arguments:
            src_texts (`List[str]`):
                List of documents to summarize or source language texts.
            tgt_texts (`list`, *optional*):
                List of summaries or target language texts.
            max_length (`int`, *optional*):
                Controls the maximum length for encoder inputs (documents to summarize or source language texts) If
                left unset or set to `None`, this will use the predefined model maximum length if a maximum length is
                required by one of the truncation/padding parameters. If the model has no specific maximum input length
                (like XLNet) truncation/padding to a maximum length will be deactivated.
            max_target_length (`int`, *optional*):
                Controls the maximum length of decoder inputs (target language texts or summaries) If left unset or set
                to `None`, this will use the max_length value.
            padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `False`):
                Activates and controls padding. Accepts the following values:

                - `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single
                  sequence if provided).
                - `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum
                  acceptable input length for the model if that argument is not provided.
                - `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different
                  lengths).
            return_tensors (`str` or [`~utils.TensorType`], *optional*):
                If set, will return tensors instead of list of python integers. Acceptable values are:

                - `'tf'`: Return TensorFlow `tf.constant` objects.
                - `'pt'`: Return PyTorch `mindspore.Tensor` objects.
                - `'np'`: Return Numpy `np.ndarray` objects.
            truncation (`bool`, `str` or [`~tokenization_utils_base.TruncationStrategy`], *optional*, defaults to `True`):
                Activates and controls truncation. Accepts the following values:

                - `True` or `'longest_first'`: Truncate to a maximum length specified with the argument `max_length` or
                  to the maximum acceptable input length for the model if that argument is not provided. This will
                  truncate token by token, removing a token from the longest sequence in the pair if a pair of
                  sequences (or a batch of pairs) is provided.
                - `'only_first'`: Truncate to a maximum length specified with the argument `max_length` or to the
                  maximum acceptable input length for the model if that argument is not provided. This will only
                  truncate the first sequence of a pair if a pair of sequences (or a batch of pairs) is provided.
                - `'only_second'`: Truncate to a maximum length specified with the argument `max_length` or to the
                  maximum acceptable input length for the model if that argument is not provided. This will only
                  truncate the second sequence of a pair if a pair of sequences (or a batch of pairs) is provided.
                - `False` or `'do_not_truncate'` (default): No truncation (i.e., can output batch with sequence lengths
                  greater than the model maximum admissible input size).
            **kwargs:
                Additional keyword arguments passed along to `self.__call__`.

        Returns:
            [`BatchEncoding`]: A [`BatchEncoding`] with the following fields:

            - **input_ids** -- List of token ids to be fed to the encoder.
            - **attention_mask** -- List of indices specifying which tokens should be attended to by the model.
            - **labels** -- List of token ids for tgt_texts.

            The full set of keys `[input_ids, attention_mask, labels]`, will only be returned if tgt_texts is passed.
            Otherwise, input_ids, attention_mask will be the only keys.
        """
        # docstyle-ignore
        formatted_warning = """
`prepare_seq2seq_batch` is deprecated and will be removed in version 5 of HuggingFace Transformers. Use the regular
`__call__` method to prepare your inputs and targets.

Here is a short example:

model_inputs = tokenizer(src_texts, text_target=tgt_texts, ...)

If you either need to use different keyword arguments for the source and target texts, you should do two calls like
this:

model_inputs = tokenizer(src_texts, ...)
labels = tokenizer(text_target=tgt_texts, ...)
model_inputs["labels"] = labels["input_ids"]

See the documentation of your specific tokenizer for more details on the specific arguments to the tokenizer of choice.
For a more complete example, see the implementation of `prepare_seq2seq_batch`.
"""
        warnings.warn(formatted_warning, FutureWarning)
        # mBART-specific kwargs that should be ignored by other models.
        kwargs.pop("src_lang", None)
        kwargs.pop("tgt_lang", None)
        if max_length is None:
            max_length = self.model_max_length
        model_inputs = self(
            src_texts,
            add_special_tokens=True,
            return_tensors=return_tensors,
            max_length=max_length,
            padding=padding,
            truncation=truncation,
            **kwargs,
        )
        if tgt_texts is None:
            return model_inputs
        # Process tgt_texts
        if max_target_length is None:
            max_target_length = max_length
        with self.as_target_tokenizer():
            labels = self(
                tgt_texts,
                add_special_tokens=True,
                return_tensors=return_tensors,
                padding=padding,
                max_length=max_target_length,
                truncation=truncation,
                **kwargs,
            )
        model_inputs["labels"] = labels["input_ids"]
        return model_inputs

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.register_for_auto_class(auto_class='AutoTokenizer') classmethod

Register this class with a given auto class. This should only be used for custom tokenizers as the ones in the library are already mapped with AutoTokenizer.

This API is experimental and may have some slight breaking changes in the next releases.

PARAMETER	DESCRIPTION
auto_class	The auto class to register this new tokenizer with. TYPE: `str` or `type`, *optional*, defaults to `"AutoTokenizer"` DEFAULT: 'AutoTokenizer'

Source code in mindnlp/transformers/tokenization_utils_base.py

@classmethod
def register_for_auto_class(cls, auto_class="AutoTokenizer"):
    """
    Register this class with a given auto class. This should only be used for custom tokenizers as the ones in the
    library are already mapped with `AutoTokenizer`.

    <Tip warning={true}>

    This API is experimental and may have some slight breaking changes in the next releases.

    </Tip>

    Args:
        auto_class (`str` or `type`, *optional*, defaults to `"AutoTokenizer"`):
            The auto class to register this new tokenizer with.
    """
    if not isinstance(auto_class, str):
        auto_class = auto_class.__name__

    import mindnlp.transformers.models.auto as auto_module

    if not hasattr(auto_module, auto_class):
        raise ValueError(f"{auto_class} is not a valid auto class.")

    cls._auto_class = auto_class

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.save_pretrained(save_directory, legacy_format=None, filename_prefix=None, push_to_hub=False, **kwargs)

Save the full tokenizer state.

This method make sure the full tokenizer can then be re-loaded using the [~tokenization_utils_base.PreTrainedTokenizer.from_pretrained] class method..

Warning,None This won't save modifications you may have applied to the tokenizer after the instantiation (for instance, modifying tokenizer.do_lower_case after creation).

PARAMETER	DESCRIPTION
save_directory	The path to a directory where the tokenizer will be saved. TYPE: `str` or `os.PathLike`
legacy_format	Only applicable for a fast tokenizer. If unset (default), will save the tokenizer in the unified JSON format as well as in legacy format if it exists, i.e. with tokenizer specific vocabulary and a separate added_tokens files. If False, will only save the tokenizer in the unified JSON format. This format is incompatible with "slow" tokenizers (not powered by the tokenizers library), so the tokenizer will not be able to be loaded in the corresponding "slow" tokenizer. If True, will save the tokenizer in legacy format. If the "slow" tokenizer doesn't exits, a value error is raised. TYPE: `bool`, *optional* DEFAULT: None
filename_prefix	A prefix to add to the names of the files saved by the tokenizer. TYPE: `str`, *optional* DEFAULT: None
push_to_hub	Whether or not to push your model to the Hugging Face model hub after saving it. You can specify the repository you want to push to with repo_id (will default to the name of save_directory in your namespace). TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False
kwargs	Additional key word arguments passed along to the [~utils.PushToHubMixin.push_to_hub] method. TYPE: `Dict[str, Any]`, *optional* DEFAULT: {}

RETURNS	DESCRIPTION
Tuple[str]	A tuple of str: The files saved.

Source code in mindnlp/transformers/tokenization_utils_base.py

def save_pretrained(
    self,
    save_directory: Union[str, os.PathLike],
    legacy_format: Optional[bool] = None,
    filename_prefix: Optional[str] = None,
    push_to_hub: bool = False,
    **kwargs,
) -> Tuple[str]:
    """
    Save the full tokenizer state.

    This method make sure the full tokenizer can then be re-loaded using the
    [`~tokenization_utils_base.PreTrainedTokenizer.from_pretrained`] class method..

    Warning,None This won't save modifications you may have applied to the tokenizer after the instantiation (for
    instance, modifying `tokenizer.do_lower_case` after creation).

    Args:
        save_directory (`str` or `os.PathLike`): The path to a directory where the tokenizer will be saved.
        legacy_format (`bool`, *optional*):
            Only applicable for a fast tokenizer. If unset (default), will save the tokenizer in the unified JSON
            format as well as in legacy format if it exists, i.e. with tokenizer specific vocabulary and a separate
            added_tokens files.

            If `False`, will only save the tokenizer in the unified JSON format. This format is incompatible with
            "slow" tokenizers (not powered by the *tokenizers* library), so the tokenizer will not be able to be
            loaded in the corresponding "slow" tokenizer.

            If `True`, will save the tokenizer in legacy format. If the "slow" tokenizer doesn't exits, a value
            error is raised.
        filename_prefix (`str`, *optional*):
            A prefix to add to the names of the files saved by the tokenizer.
        push_to_hub (`bool`, *optional*, defaults to `False`):
            Whether or not to push your model to the Hugging Face model hub after saving it. You can specify the
            repository you want to push to with `repo_id` (will default to the name of `save_directory` in your
            namespace).
        kwargs (`Dict[str, Any]`, *optional*):
            Additional key word arguments passed along to the [`~utils.PushToHubMixin.push_to_hub`] method.

    Returns:
        A tuple of `str`: The files saved.
    """
    use_auth_token = kwargs.pop("use_auth_token", None)

    if use_auth_token is not None:
        warnings.warn(
            "The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.",
            FutureWarning,
        )
        if kwargs.get("token", None) is not None:
            raise ValueError(
                "`token` and `use_auth_token` are both specified. Please set only the argument `token`."
            )
        kwargs["token"] = use_auth_token

    if os.path.isfile(save_directory):
        logger.error(f"Provided path ({save_directory}) should be a directory, not a file")
        return

    os.makedirs(save_directory, exist_ok=True)

    if push_to_hub:
        repo_id = kwargs.pop("repo_id", save_directory.split(os.path.sep)[-1])
        repo_id = self._create_repo(repo_id, **kwargs)

    special_tokens_map_file = os.path.join(
        save_directory, (filename_prefix + "-" if filename_prefix else "") + SPECIAL_TOKENS_MAP_FILE
    )
    tokenizer_config_file = os.path.join(
        save_directory, (filename_prefix + "-" if filename_prefix else "") + TOKENIZER_CONFIG_FILE
    )

    tokenizer_config = copy.deepcopy(self.init_kwargs)

    # Let's save the init kwargs
    target_keys = set(self.init_kwargs.keys())
    # Let's save the special tokens map (only the strings)
    target_keys.update(["model_max_length", "clean_up_tokenization_spaces"])

    for k in target_keys:
        if hasattr(self, k):
            tokenizer_config[k] = getattr(self, k)

    # Let's make sure we properly save the special tokens.
    tokenizer_config.update(self.special_tokens_map)

    if self.chat_template is not None:
        tokenizer_config["chat_template"] = self.chat_template

    if len(self.init_inputs) > 0:
        tokenizer_config["init_inputs"] = copy.deepcopy(self.init_inputs)
    for file_id in self.vocab_files_names.keys():
        tokenizer_config.pop(file_id, None)

    # no typefields, this way old fast and slow can load it
    tokenizer_config = self.convert_added_tokens(tokenizer_config, add_type_field=True, save=True)

    # Process added tokens seperatly: allows previous versions to ignore it!
    added_tokens = {}
    for key, value in self.added_tokens_decoder.items():
        added_tokens[key] = value.__getstate__()
    tokenizer_config["added_tokens_decoder"] = added_tokens

    # Add tokenizer class to the tokenizer config to be able to reload it with from_pretrained
    tokenizer_class = self.__class__.__name__
    # Remove the Fast at the end unless we have a special `PreTrainedTokenizerFast`
    if tokenizer_class.endswith("Fast") and tokenizer_class != "PreTrainedTokenizerFast":
        tokenizer_class = tokenizer_class[:-4]
    tokenizer_config["tokenizer_class"] = tokenizer_class
    if getattr(self, "_auto_map", None) is not None:
        tokenizer_config["auto_map"] = self._auto_map
    if getattr(self, "_processor_class", None) is not None:
        tokenizer_config["processor_class"] = self._processor_class

    # remove private information
    if "name_or_path" in tokenizer_config:
        tokenizer_config.pop("name_or_path")
        tokenizer_config.pop("special_tokens_map_file", None)
        tokenizer_config.pop("tokenizer_file", None)

    with open(tokenizer_config_file, "w", encoding="utf-8") as f:
        out_str = json.dumps(tokenizer_config, indent=2, sort_keys=True, ensure_ascii=False) + "\n"
        f.write(out_str)
    logger.info(f"tokenizer config file saved in {tokenizer_config_file}")

    # Sanitize AddedTokens in special_tokens_map

    # kept for forward compatibility, will be removed in transoformers 5. Typefields are not saved for FC, special should not be save either
    write_dict = self.convert_added_tokens(self.special_tokens_map_extended, save=True, add_type_field=False)
    with open(special_tokens_map_file, "w", encoding="utf-8") as f:
        out_str = json.dumps(write_dict, indent=2, sort_keys=True, ensure_ascii=False) + "\n"
        f.write(out_str)
    logger.info(f"Special tokens file saved in {special_tokens_map_file}")

    file_names = (tokenizer_config_file, special_tokens_map_file)

    save_files = self._save_pretrained(
        save_directory=save_directory,
        file_names=file_names,
        legacy_format=legacy_format,
        filename_prefix=filename_prefix,
    )

    return save_files

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.save_vocabulary(save_directory, filename_prefix=None)

Save only the vocabulary of the tokenizer (vocabulary + added tokens).

This method won't save the configuration and special token mappings of the tokenizer. Use [~PreTrainedTokenizerFast._save_pretrained] to save the whole state of the tokenizer.

PARAMETER	DESCRIPTION
save_directory	The directory in which to save the vocabulary. TYPE: `str`
filename_prefix	An optional prefix to add to the named of the saved files. TYPE: `str`, *optional* DEFAULT: None

RETURNS	DESCRIPTION
Tuple[str]	Tuple(str): Paths to the files saved.

Source code in mindnlp/transformers/tokenization_utils_base.py

def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
    """
    Save only the vocabulary of the tokenizer (vocabulary + added tokens).

    This method won't save the configuration and special token mappings of the tokenizer. Use
    [`~PreTrainedTokenizerFast._save_pretrained`] to save the whole state of the tokenizer.

    Args:
        save_directory (`str`):
            The directory in which to save the vocabulary.
        filename_prefix (`str`, *optional*):
            An optional prefix to add to the named of the saved files.

    Returns:
        `Tuple(str)`: Paths to the files saved.
    """
    raise NotImplementedError

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.tokenize(text, pair=None, add_special_tokens=False, **kwargs)

Converts a string in a sequence of tokens, replacing unknown tokens with the unk_token.

PARAMETER	DESCRIPTION
text	The sequence to be encoded. TYPE: `str`
pair	A second sequence to be encoded with the first. TYPE: `str`, *optional* DEFAULT: None
add_special_tokens	Whether or not to add the special tokens associated with the corresponding model. TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False
kwargs	Will be passed to the underlying model specific encode method. See details in [~PreTrainedTokenizerBase.__call__] TYPE: additional keyword arguments, *optional* DEFAULT: {}

RETURNS	DESCRIPTION
List[str]	List[str]: The list of tokens.

Source code in mindnlp/transformers/tokenization_utils_base.py

def tokenize(self, text: str, pair: Optional[str] = None, add_special_tokens: bool = False, **kwargs) -> List[str]:
    """
    Converts a string in a sequence of tokens, replacing unknown tokens with the `unk_token`.

    Args:
        text (`str`):
            The sequence to be encoded.
        pair (`str`, *optional*):
            A second sequence to be encoded with the first.
        add_special_tokens (`bool`, *optional*, defaults to `False`):
            Whether or not to add the special tokens associated with the corresponding model.
        kwargs (additional keyword arguments, *optional*):
            Will be passed to the underlying model specific encode method. See details in
            [`~PreTrainedTokenizerBase.__call__`]

    Returns:
        `List[str]`: The list of tokens.
    """
    raise NotImplementedError

mindnlp.transformers.tokenization_utils_base.PreTrainedTokenizerBase.truncate_sequences(ids, pair_ids=None, num_tokens_to_remove=0, truncation_strategy='longest_first', stride=0)

Truncates a sequence pair in-place following the strategy.

PARAMETER	DESCRIPTION
ids	Tokenized input ids of the first sequence. Can be obtained from a string by chaining the tokenize and convert_tokens_to_ids methods. TYPE: `List[int]`
pair_ids	Tokenized input ids of the second sequence. Can be obtained from a string by chaining the tokenize and convert_tokens_to_ids methods. TYPE: `List[int]`, *optional* DEFAULT: None
num_tokens_to_remove	Number of tokens to remove using the truncation strategy. TYPE: `int`, *optional*, defaults to 0 DEFAULT: 0
truncation_strategy	The strategy to follow for truncation. Can be: 'longest_first': Truncate to a maximum length specified with the argument max_length or to the maximum acceptable input length for the model if that argument is not provided. This will truncate token by token, removing a token from the longest sequence in the pair if a pair of sequences (or a batch of pairs) is provided. 'only_first': Truncate to a maximum length specified with the argument max_length or to the maximum acceptable input length for the model if that argument is not provided. This will only truncate the first sequence of a pair if a pair of sequences (or a batch of pairs) is provided. 'only_second': Truncate to a maximum length specified with the argument max_length or to the maximum acceptable input length for the model if that argument is not provided. This will only truncate the second sequence of a pair if a pair of sequences (or a batch of pairs) is provided. 'do_not_truncate' (default): No truncation (i.e., can output batch with sequence lengths greater than the model maximum admissible input size). TYPE: `str` or [`~tokenization_utils_base.TruncationStrategy`], *optional*, defaults to `False` DEFAULT: 'longest_first'
stride	If set to a positive number, the overflowing tokens returned will contain some tokens from the main sequence returned. The value of this argument defines the number of additional tokens. TYPE: `int`, *optional*, defaults to 0 DEFAULT: 0

RETURNS	DESCRIPTION
List[int]	Tuple[List[int], List[int], List[int]]: The truncated ids, the truncated pair_ids and the list of
List[int]	overflowing tokens. Note: The longest_first strategy returns empty list of overflowing tokens if a pair
List[int]	of sequences (or a batch of pairs) is provided.

Source code in mindnlp/transformers/tokenization_utils_base.py

def truncate_sequences(
    self,
    ids: List[int],
    pair_ids: Optional[List[int]] = None,
    num_tokens_to_remove: int = 0,
    truncation_strategy: Union[str, TruncationStrategy] = "longest_first",
    stride: int = 0,
) -> Tuple[List[int], List[int], List[int]]:
    """
    Truncates a sequence pair in-place following the strategy.

    Args:
        ids (`List[int]`):
            Tokenized input ids of the first sequence. Can be obtained from a string by chaining the `tokenize` and
            `convert_tokens_to_ids` methods.
        pair_ids (`List[int]`, *optional*):
            Tokenized input ids of the second sequence. Can be obtained from a string by chaining the `tokenize`
            and `convert_tokens_to_ids` methods.
        num_tokens_to_remove (`int`, *optional*, defaults to 0):
            Number of tokens to remove using the truncation strategy.
        truncation_strategy (`str` or [`~tokenization_utils_base.TruncationStrategy`], *optional*, defaults to `False`):
            The strategy to follow for truncation. Can be:

            - `'longest_first'`: Truncate to a maximum length specified with the argument `max_length` or to the
              maximum acceptable input length for the model if that argument is not provided. This will truncate
              token by token, removing a token from the longest sequence in the pair if a pair of sequences (or a
              batch of pairs) is provided.
            - `'only_first'`: Truncate to a maximum length specified with the argument `max_length` or to the
              maximum acceptable input length for the model if that argument is not provided. This will only
              truncate the first sequence of a pair if a pair of sequences (or a batch of pairs) is provided.
            - `'only_second'`: Truncate to a maximum length specified with the argument `max_length` or to the
              maximum acceptable input length for the model if that argument is not provided. This will only
              truncate the second sequence of a pair if a pair of sequences (or a batch of pairs) is provided.
            - `'do_not_truncate'` (default): No truncation (i.e., can output batch with sequence lengths greater
              than the model maximum admissible input size).
        stride (`int`, *optional*, defaults to 0):
            If set to a positive number, the overflowing tokens returned will contain some tokens from the main
            sequence returned. The value of this argument defines the number of additional tokens.

    Returns:
        `Tuple[List[int], List[int], List[int]]`: The truncated `ids`, the truncated `pair_ids` and the list of
        overflowing tokens. Note: The *longest_first* strategy returns empty list of overflowing tokens if a pair
        of sequences (or a batch of pairs) is provided.
    """
    if num_tokens_to_remove <= 0:
        return ids, pair_ids, []

    if not isinstance(truncation_strategy, TruncationStrategy):
        truncation_strategy = TruncationStrategy(truncation_strategy)

    overflowing_tokens = []
    if truncation_strategy == TruncationStrategy.ONLY_FIRST or (
        truncation_strategy == TruncationStrategy.LONGEST_FIRST and pair_ids is None
    ):
        if len(ids) > num_tokens_to_remove:
            window_len = min(len(ids), stride + num_tokens_to_remove)
            if self.truncation_side == "left":
                overflowing_tokens = ids[:window_len]
                ids = ids[num_tokens_to_remove:]
            elif self.truncation_side == "right":
                overflowing_tokens = ids[-window_len:]
                ids = ids[:-num_tokens_to_remove]
            else:
                raise ValueError(f"invalid truncation strategy: {self.truncation_side}, use 'left' or 'right'.")

        else:
            error_msg = (
                f"We need to remove {num_tokens_to_remove} to truncate the input "
                f"but the first sequence has a length {len(ids)}. "
            )
            if truncation_strategy == TruncationStrategy.ONLY_FIRST:
                error_msg = (
                    error_msg + "Please select another truncation strategy than "
                    f"{truncation_strategy}, for instance 'longest_first' or 'only_second'."
                )
            logger.error(error_msg)
    elif truncation_strategy == TruncationStrategy.LONGEST_FIRST:
        logger.warning(
            "Be aware, overflowing tokens are not returned for the setting you have chosen,"
            f" i.e. sequence pairs with the '{TruncationStrategy.LONGEST_FIRST.value}' "
            "truncation strategy. So the returned list will always be empty even if some "
            "tokens have been removed."
        )
        for _ in range(num_tokens_to_remove):
            if pair_ids is None or len(ids) > len(pair_ids):
                if self.truncation_side == "right":
                    ids = ids[:-1]
                elif self.truncation_side == "left":
                    ids = ids[1:]
                else:
                    raise ValueError("invalid truncation strategy:" + str(self.truncation_side))
            else:
                if self.truncation_side == "right":
                    pair_ids = pair_ids[:-1]
                elif self.truncation_side == "left":
                    pair_ids = pair_ids[1:]
                else:
                    raise ValueError("invalid truncation strategy:" + str(self.truncation_side))
    elif truncation_strategy == TruncationStrategy.ONLY_SECOND and pair_ids is not None:
        if len(pair_ids) > num_tokens_to_remove:
            window_len = min(len(pair_ids), stride + num_tokens_to_remove)
            if self.truncation_side == "right":
                overflowing_tokens = pair_ids[-window_len:]
                pair_ids = pair_ids[:-num_tokens_to_remove]
            elif self.truncation_side == "left":
                overflowing_tokens = pair_ids[:window_len]
                pair_ids = pair_ids[num_tokens_to_remove:]
            else:
                raise ValueError("invalid truncation strategy:" + str(self.truncation_side))
        else:
            logger.error(
                f"We need to remove {num_tokens_to_remove} to truncate the input "
                f"but the second sequence has a length {len(pair_ids)}. "
                f"Please select another truncation strategy than {truncation_strategy}, "
                "for instance 'longest_first' or 'only_first'."
            )

    return (ids, pair_ids, overflowing_tokens)

mindnlp.transformers.tokenization_utils_base.SpecialTokensMixin

A mixin derived by [PreTrainedTokenizer] and [PreTrainedTokenizerFast] to handle specific behaviors related to special tokens. In particular, this class hold the attributes which can be used to directly access these special tokens in a model-independent manner and allow to set and update the special tokens.

PARAMETER	DESCRIPTION
bos_token	A special token representing the beginning of a sentence. TYPE: `str` or `tokenizers.AddedToken`, *optional*
eos_token	A special token representing the end of a sentence. TYPE: `str` or `tokenizers.AddedToken`, *optional*
unk_token	A special token representing an out-of-vocabulary token. TYPE: `str` or `tokenizers.AddedToken`, *optional*
sep_token	A special token separating two different sentences in the same input (used by BERT for instance). TYPE: `str` or `tokenizers.AddedToken`, *optional*
pad_token	A special token used to make arrays of tokens the same size for batching purpose. Will then be ignored by attention mechanisms or loss computation. TYPE: `str` or `tokenizers.AddedToken`, *optional*
cls_token	A special token representing the class of the input (used by BERT for instance). TYPE: `str` or `tokenizers.AddedToken`, *optional*
mask_token	A special token representing a masked token (used by masked-language modeling pretraining objectives, like BERT). TYPE: `str` or `tokenizers.AddedToken`, *optional*
additional_special_tokens	A tuple or a list of additional tokens, which will be marked as special, meaning that they will be skipped when decoding if skip_special_tokens is set to True. TYPE: tuple or list of `str` or `tokenizers.AddedToken`, *optional*

Source code in mindnlp/transformers/tokenization_utils_base.py

800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210