def from_pretrained()

in src/transformers/models/auto/tokenization_auto.py [0:0]


    def from_pretrained(cls, pretrained_model_name_or_path, *inputs, **kwargs):
        r"""
        Instantiate one of the tokenizer classes of the library from a pretrained model vocabulary.

        The tokenizer class to instantiate is selected based on the `model_type` property of the config object (either
        passed as an argument or loaded from `pretrained_model_name_or_path` if possible), or when it's missing, by
        falling back to using pattern matching on `pretrained_model_name_or_path`:

        List options

        Params:
            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 huggingface.co.
                    - A path to a *directory* containing vocabulary files required by the tokenizer, for instance saved
                      using the [`~PreTrainedTokenizer.save_pretrained`] method, e.g., `./my_model_directory/`.
                    - 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`. (Not
                      applicable to all derived classes)
            inputs (additional positional arguments, *optional*):
                Will be passed along to the Tokenizer `__init__()` method.
            config ([`PretrainedConfig`], *optional*)
                The configuration object used to determine the tokenizer class to instantiate.
            cache_dir (`str` or `os.PathLike`, *optional*):
                Path to a directory in which a downloaded pretrained model configuration 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 model weights and configuration files and override the
                cached versions if they exist.
            resume_download:
                Deprecated and ignored. All downloads are now resumed by default when possible.
                Will be removed in v5 of Transformers.
            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.
            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 huggingface.co, 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 huggingface.co (e.g. for
                facebook/rag-token-base), specify it here.
            use_fast (`bool`, *optional*, defaults to `True`):
                Use a [fast Rust-based tokenizer](https://huggingface.co/docs/tokenizers/index) if it is supported for
                a given model. If a fast tokenizer is not available for a given model, a normal Python-based tokenizer
                is returned instead.
            tokenizer_type (`str`, *optional*):
                Tokenizer type to be loaded.
            trust_remote_code (`bool`, *optional*, defaults to `False`):
                Whether or not to allow for custom models defined on the Hub in their own modeling files. This option
                should only be set to `True` for repositories you trust and in which you have read the code, as it will
                execute code present on the Hub on your local machine.
            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.

        Examples:

        ```python
        >>> from transformers import AutoTokenizer

        >>> # Download vocabulary from huggingface.co and cache.
        >>> tokenizer = AutoTokenizer.from_pretrained("google-bert/bert-base-uncased")

        >>> # Download vocabulary from huggingface.co (user-uploaded) and cache.
        >>> tokenizer = AutoTokenizer.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 = AutoTokenizer.from_pretrained("./test/bert_saved_model/")

        >>> # Download vocabulary from huggingface.co and define model-specific arguments
        >>> tokenizer = AutoTokenizer.from_pretrained("FacebookAI/roberta-base", add_prefix_space=True)
        ```"""
        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

        config = kwargs.pop("config", None)
        kwargs["_from_auto"] = True

        use_fast = kwargs.pop("use_fast", True)
        tokenizer_type = kwargs.pop("tokenizer_type", None)
        trust_remote_code = kwargs.pop("trust_remote_code", None)
        gguf_file = kwargs.get("gguf_file", None)

        # First, let's see whether the tokenizer_type is passed so that we can leverage it
        if tokenizer_type is not None:
            tokenizer_class = None
            tokenizer_class_tuple = TOKENIZER_MAPPING_NAMES.get(tokenizer_type, None)

            if tokenizer_class_tuple is None:
                raise ValueError(
                    f"Passed `tokenizer_type` {tokenizer_type} does not exist. `tokenizer_type` should be one of "
                    f"{', '.join(c for c in TOKENIZER_MAPPING_NAMES.keys())}."
                )

            tokenizer_class_name, tokenizer_fast_class_name = tokenizer_class_tuple

            if use_fast:
                if tokenizer_fast_class_name is not None:
                    tokenizer_class = tokenizer_class_from_name(tokenizer_fast_class_name)
                else:
                    logger.warning(
                        "`use_fast` is set to `True` but the tokenizer class does not have a fast version. "
                        " Falling back to the slow version."
                    )
            if tokenizer_class is None:
                tokenizer_class = tokenizer_class_from_name(tokenizer_class_name)

            if tokenizer_class is None:
                raise ValueError(f"Tokenizer class {tokenizer_class_name} is not currently imported.")

            return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)

        # Next, let's try to use the tokenizer_config file to get the tokenizer class.
        tokenizer_config = get_tokenizer_config(pretrained_model_name_or_path, **kwargs)
        if "_commit_hash" in tokenizer_config:
            kwargs["_commit_hash"] = tokenizer_config["_commit_hash"]
        config_tokenizer_class = tokenizer_config.get("tokenizer_class")
        tokenizer_auto_map = None
        if "auto_map" in tokenizer_config:
            if isinstance(tokenizer_config["auto_map"], (tuple, list)):
                # Legacy format for dynamic tokenizers
                tokenizer_auto_map = tokenizer_config["auto_map"]
            else:
                tokenizer_auto_map = tokenizer_config["auto_map"].get("AutoTokenizer", None)

        # If that did not work, let's try to use the config.
        if config_tokenizer_class is None:
            if not isinstance(config, PretrainedConfig):
                if gguf_file:
                    gguf_path = cached_file(pretrained_model_name_or_path, gguf_file, **kwargs)
                    config_dict = load_gguf_checkpoint(gguf_path, return_tensors=False)["config"]
                    config = AutoConfig.for_model(**config_dict)
                else:
                    config = AutoConfig.from_pretrained(
                        pretrained_model_name_or_path, trust_remote_code=trust_remote_code, **kwargs
                    )
            config_tokenizer_class = config.tokenizer_class
            if hasattr(config, "auto_map") and "AutoTokenizer" in config.auto_map:
                tokenizer_auto_map = config.auto_map["AutoTokenizer"]

        has_remote_code = tokenizer_auto_map is not None
        has_local_code = type(config) in TOKENIZER_MAPPING or (
            config_tokenizer_class is not None
            and (
                tokenizer_class_from_name(config_tokenizer_class) is not None
                or tokenizer_class_from_name(config_tokenizer_class + "Fast") is not None
            )
        )
        if has_remote_code:
            if use_fast and tokenizer_auto_map[1] is not None:
                class_ref = tokenizer_auto_map[1]
            else:
                class_ref = tokenizer_auto_map[0]
            if "--" in class_ref:
                upstream_repo = class_ref.split("--")[0]
            else:
                upstream_repo = None
            trust_remote_code = resolve_trust_remote_code(
                trust_remote_code, pretrained_model_name_or_path, has_local_code, has_remote_code, upstream_repo
            )

        if has_remote_code and trust_remote_code:
            tokenizer_class = get_class_from_dynamic_module(class_ref, pretrained_model_name_or_path, **kwargs)
            _ = kwargs.pop("code_revision", None)
            tokenizer_class.register_for_auto_class()
            return tokenizer_class.from_pretrained(
                pretrained_model_name_or_path, *inputs, trust_remote_code=trust_remote_code, **kwargs
            )
        elif config_tokenizer_class is not None:
            tokenizer_class = None
            if use_fast and not config_tokenizer_class.endswith("Fast"):
                tokenizer_class_candidate = f"{config_tokenizer_class}Fast"
                tokenizer_class = tokenizer_class_from_name(tokenizer_class_candidate)
            if tokenizer_class is None:
                tokenizer_class_candidate = config_tokenizer_class
                tokenizer_class = tokenizer_class_from_name(tokenizer_class_candidate)
            if tokenizer_class is None:
                raise ValueError(
                    f"Tokenizer class {tokenizer_class_candidate} does not exist or is not currently imported."
                )
            return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)

        # Otherwise we have to be creative.
        # if model is an encoder decoder, the encoder tokenizer class is used by default
        if isinstance(config, EncoderDecoderConfig):
            if type(config.decoder) is not type(config.encoder):  # noqa: E721
                logger.warning(
                    f"The encoder model config class: {config.encoder.__class__} is different from the decoder model "
                    f"config class: {config.decoder.__class__}. It is not recommended to use the "
                    "`AutoTokenizer.from_pretrained()` method in this case. Please use the encoder and decoder "
                    "specific tokenizer classes."
                )
            config = config.encoder

        model_type = config_class_to_model_type(type(config).__name__)
        if model_type is not None:
            tokenizer_class_py, tokenizer_class_fast = TOKENIZER_MAPPING[type(config)]

            if tokenizer_class_fast and (use_fast or tokenizer_class_py is None):
                return tokenizer_class_fast.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
            else:
                if tokenizer_class_py is not None:
                    return tokenizer_class_py.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
                else:
                    raise ValueError(
                        "This tokenizer cannot be instantiated. Please make sure you have `sentencepiece` installed "
                        "in order to use this tokenizer."
                    )

        raise ValueError(
            f"Unrecognized configuration class {config.__class__} to build an AutoTokenizer.\n"
            f"Model type should be one of {', '.join(c.__name__ for c in TOKENIZER_MAPPING.keys())}."
        )