U ,-e@s UdZddlZddlZddlZddlZddlmZddlmZm Z m Z m Z m Z ddl mZddlmZmZddlmZdd lmZdd lmZmZmZmZmZd d lmZd dlmZd dl m!Z!m"Z"m#Z#m$Z$m%Z%erddl&m'Z'ndZ'e(e)Z*er$eZ+ee,e e e,e e,ffe-d< n$eder4dnderBdndffdderXdndffdderndndffdderdnderdndffddderdndffderd nddffd!d"d#erd$nderd%ndffd&d'erd(ndffd)d*d+d,derdndffd-d.er.d/ndffd0derDd1ndffd2d3erZd4ndffd5derpdndffd6d7erd8nderd9ndffd:d;derdndffderd?ndffd@d>erd?ndffdAerdBnderdCndffdDdEer&dFndffdGdHererd?ndffdxdyerdzndffd{d|d3er4d4ndffd}derJd~ndffdd.er`d/ndffddderxdndffdderdndffdderdndffdderdndffdderdndffdderdndffderdnderd~ndffdderdndffder2dnder@dndffddderXdndffderldnddffderdnddffderdnderdndffderdnderdndffdd3erd4ndffdderdndffdder dnderd~ndffder,dnddffdderDdndffdderZdndffdderpdsndffdd3erd4ndffderdnderdndffdderdndffdderdndffdderdndffderdnder dndffder dnder.dndffderBdnderPdndffdd>erfd?ndffdder|dndffdd.erd/ndffdd>erd?ndffderd'nderd(ndffderd'nderd(ndffdde rdnde rd~ndffddde r(dndffde re r4d?ndffde rJdnde rZdndffdde rvdnddffde rdnde rdndffde rdnde rȐdndffd e rd nde rd ndffd e rdnde rdndffd e r.dnde rsr+) class_namec Cs|dkr tStD]T\}}||krt|}td|d}zt||WStk rfYqYqXqtj D].\}}|D] }t|dd|kr|Sqqttd}t ||rt||SdS)Nr.ztransformers.models__name__Z transformers) rritemsr importlib import_modulegetattrAttributeErrorTOKENIZER_MAPPING_extra_contenthasattr)r, module_nameZ tokenizersmoduleconfigZ tokenizerZ main_moduler&r&r*tokenizer_class_from_names$    r:F) pretrained_model_name_or_path cache_dirforce_downloadresume_downloadproxiestokenrevisionlocal_files_only subfolderc Ks| dd} | dk r4tdt|dk r0td| }| dd} t|t||||||||dd| d } | dkrxt diSt | | } t | d d } t | }W5QRX| |d<|S) a Loads the tokenizer configuration from a pretrained model tokenizer configuration. Args: pretrained_model_name_or_path (`str` or `os.PathLike`): This can be either: - a string, the *model id* of a pretrained model configuration hosted inside a model repo on huggingface.co. 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 a configuration file saved using the [`~PreTrainedTokenizer.save_pretrained`] method, e.g., `./my_model_directory/`. 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 to (re-)download the configuration files and override the cached versions if they exist. resume_download (`bool`, *optional*, defaults to `False`): Whether or not to delete incompletely received file. Attempts 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`). 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. local_files_only (`bool`, *optional*, defaults to `False`): If `True`, will only try to load the tokenizer configuration from local files. subfolder (`str`, *optional*, defaults to `""`): In case the tokenizer config is located inside a subfolder of the model repo on huggingface.co, you can specify the folder name here. Passing `token=True` is required when you want to use a private model. Returns: `Dict`: The configuration of the tokenizer. Examples: ```python # Download configuration from huggingface.co and cache. tokenizer_config = get_tokenizer_config("bert-base-uncased") # This model does not have a tokenizer config so the result will be an empty dict. tokenizer_config = get_tokenizer_config("xlm-roberta-base") # Save a pretrained tokenizer locally and you can reload its config from transformers import AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("bert-base-cased") tokenizer.save_pretrained("tokenizer-test") tokenizer_config = get_tokenizer_config("tokenizer-test") ```use_auth_tokenNVThe `use_auth_token` argument is deprecated and will be removed in v5 of Transformers.V`token` and `use_auth_token` are both specified. Please set only the argument `token`. _commit_hashF) r=r>r?r@rArBrCrDZ%_raise_exceptions_for_missing_entriesZ'_raise_exceptions_for_connection_errorsrHz\Could not locate the tokenizer configuration file, will try to use the model config instead.zutf-8)encoding)popwarningswarn FutureWarning ValueErrorgetrr loggerinforopenjsonload)r<r=r>r?r@rArBrCrDkwargsrEZ commit_hashZresolved_config_filereaderresultr&r&r*get_tokenizer_configsBI    rXc@s6eZdZdZddZeeeddZd dd Z dS) AutoTokenizera This is a generic tokenizer class that will be instantiated as one of the tokenizer classes of the library when created with the [`AutoTokenizer.from_pretrained`] class method. This class cannot be instantiated directly using `__init__()` (throws an error). cCs tddS)Nz}AutoTokenizer is designed to be instantiated using the `AutoTokenizer.from_pretrained(pretrained_model_name_or_path)` method.)EnvironmentError)selfr&r&r*__init__8szAutoTokenizer.__init__c Os|dd}|dk r@tdt|dddk r8td||d<|dd}d|d<|d d}|d d}|d d}|dk r(d} t|d} | dkrtd |d dddtDd| \} } |r| dk rt | } n t d| dkrt | } | dkrtd| d| j |f||St |f|} d| krJ| d|d<| d}d}d| krt| dttfr| d}n| ddd}|dkrt|tstj |fd |i|}|j}t|drd|jkr|jd}|dk }|dk pt|tk}t||||}|r|r|r:|ddk r:|d}n|d}t||f|} |dd}tj|rr| | j |f||S|dk rd} |r|ds|d}t |} | dkr|}t |} | dkrtd|d| j |f||St|tr@t|j t|j!k r:t d|j!j"d|j j"d |j!}t#t|j$}|dk rtt|\}}|r|s~|dkr|j |f||S|dk r|j |f||Std!td"|j"d#dd$dtDddS)%a8 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. 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 [`~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 (`bool`, *optional*, defaults to `False`): Whether or not to delete incompletely received files. Will 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. 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("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("roberta-base", add_prefix_space=True) ```rENrFrArGr9TZ _from_autouse_fasttokenizer_typetrust_remote_codezPassed `tokenizer_type` z3 does not exist. `tokenizer_type` should be one of z, css|] }|VqdSNr&r'cr&r&r* sz0AutoTokenizer.from_pretrained..r-zt`use_fast` is set to `True` but the tokenizer class does not have a fast version. Falling back to the slow version.zTokenizer class z is not currently imported.rHtokenizer_classauto_maprYrrZ code_revisionZFastz- does not exist or is not currently imported.z The encoder model config class: z3 is different from the decoder model config class: z. It is not recommended to use the `AutoTokenizer.from_pretrained()` method in this case. Please use the encoder and decoder specific tokenizer classes.zzThis tokenizer cannot be instantiated. Please make sure you have `sentencepiece` installed in order to use this tokenizer.z!Unrecognized configuration class z8 to build an AutoTokenizer. Model type should be one of css|] }|jVqdSr`)r.rar&r&r*rc s)%rJrKrLrMrOrNrjoinkeysr:rPwarningfrom_pretrainedrX isinstancetuplelistr rrdr6retyper4r r ospathisdirZregister_for_auto_classendswithrdecoderencoder __class__rr.)clsr<inputsrUrEr9r]r^r_rdZtokenizer_class_tupleZtokenizer_class_nameZtokenizer_fast_class_nameZtokenizer_configZconfig_tokenizer_classZtokenizer_auto_mapZhas_remote_codeZhas_local_codeZ class_ref_Ztokenizer_class_candidateZ model_typeZtokenizer_class_pyZtokenizer_class_fastr&r&r*ri>sO       $                      &zAutoTokenizer.from_pretrainedNFcCs|dkr|dkrtd|dk r2t|tr2td|dk rLt|trLtd|dk r|dk rt|tr|j|krtd|jd|d|tjkrt|\}}|dkr|}|dkr|}tj|||f|ddS) a Register a new tokenizer in this mapping. Args: config_class ([`PretrainedConfig`]): The configuration corresponding to the model to register. slow_tokenizer_class ([`PretrainedTokenizer`], *optional*): The slow tokenizer to register. fast_tokenizer_class ([`PretrainedTokenizerFast`], *optional*): The fast tokenizer to register. NzKYou need to pass either a `slow_tokenizer_class` or a `fast_tokenizer_classz:You passed a fast tokenizer in the `slow_tokenizer_class`.z:You passed a slow tokenizer in the `fast_tokenizer_class`.zThe fast tokenizer class you are passing has a `slow_tokenizer_class` attribute that is not consistent with the slow tokenizer class you passed (fast tokenizer has z and you passed z!. Fix one of those so they match!)exist_ok)rN issubclassrr slow_tokenizer_classr4r5register)Z config_classrzZfast_tokenizer_classrxZ existing_slowZ existing_fastr&r&r*r{s0   zAutoTokenizer.register)NNF) r. __module__ __qualname____doc__r\ classmethodrrrir{r&r&r&r*rY0s QrY)NFFNNNFr;)6r~r0rSrnrK collectionsrtypingrrrrrZconfiguration_utilsr Zdynamic_module_utilsr r Ztokenization_utilsr Ztokenization_utils_baser utilsrrrrrZencoder_decoderrZ auto_factoryrZconfiguration_autorrrrrZtokenization_utils_fastrZ get_loggerr.rPrstr__annotations__r4r/ZCONFIG_TO_TYPEr:PathLikeboolrXrYr&r&r&r*s        *o  m