U 4Af@sUdZddlZddlZddlZddlZddlmZddlmZm Z m Z m Z m Z ddl mZddlmZmZddlmZdd lmZdd lmZdd lmZmZmZmZmZmZd d lm Z ddl!m"Z"ddl#m$Z$m%Z%m&Z&m'Z'm(Z(erddl)m*Z*ndZ*e+e,Z-er4eZ.ee/e e e/e e/ffe0d<n>ederDdnderRdndffdderhdndffdder~dndffdderdnderdndffddderdndffd erd!nddffd"d#d$erd%nderd&ndffd'd(er d)ndffd*d+d,d-der(dndffd.d/er>d0ndffd1derTd2ndffd3d4erjd5ndffd6derdndffd7d8erd9nderd:ndffd;dndffd?derdndffd@d4erd5ndffdAdBer dCndffdDdBer dCndffdEdFer6dGnderDdHndffdIdJerZdKndffdLderpdMndffdNdOerdPndffdQerdRnderdSndffdTdUdVdWd4erd5ndffdXd/erd0ndffdYdZerd[ndffd\erd]nderd^ndffd_d`er(dandffdbdcer>ddndffdedferTdgndffdhderjdndffdier~djnddffdkdlderdmndffdnerdonddffdpdqdrerdsndffdtdudverdwndffdxerdynderdzndffd{erdynder"dzndffd|der8dndffd}erLd~nddffdd/erdd0ndffdd/erzd0ndffdd/erd0ndffdderdndffddd/erd0ndffddderdndffddBerdCndffdderdndffddd4erd5ndffdder0d>ndffdd=erFd>ndffdd/er\d0ndffdd/errd0ndffderd=nderd>ndffderd=nderd>ndffdderdnderdndffdderdndffdderdndffdderdndffdder2dndffdderHdndffdder^dndffderrd=nderd>ndffdd=erd>ndffdd=erd>ndffdd=erd>ndffdderdndffderdnderdndffddderdndffder&dnddffdder>dndffdderTdndffderhdnddffder~dnderdndffderdnderdndffdd4erd5ndffdderdndffdderd=nderd>ndffde rd=nde r d>ndffde r4dnddffdde rLdndffdde rbdndffdde rxdndffdd4e rd5ndffde rdnde rdndffdde rdndffdde rdndffdde rdndffdde rdndffde rdnde r*dndffde r>dnde rLdndffde r`dnde rndndffdde rdndffddBe rdCndffdde rdndffdd/e rd0ndffddBe rdCndffddBe rdCndffdd=e rd>ndffde rd(nde r*d)ndffde r>d(nde rLd)ndffdde rbd=nde rpd>ndffddJe rdKndffdd=e rd>ndffddde rdndffde rdnddffddde rdndffdde rdndffdde rdndffddde r&dndffde r:dynde rHdzndffde r\dnde rjdndffde rdnde rdndffdde rdndffdd4e rd5ndffdd4e rd5ndffdd d e rd ndffd de rdndffd e r.dnde r>dndffde rVdnde rfdndffde r~dnddffde rdnddffdde rdnddffddde rؐdndffdde rdndffdd/erd0ndffderdnder,dndffderBdnderPdndffd d!d"d#dertdndffd$erd%nderd&ndffd'erdnderdndffd(d=erd>ndffd)derdndffd*d=erd>ndffd+der dndffd,d-d.d/d0d1d2erPd3ndffd4dBerhdCndffd5erd6nderd7ndffd8d9erd:nddffd;erdnderdndffdnderd?ndffd@er4dnderBdndffdAerXdnderfdndffgZ.e"e$e.Z1dBdCe$2DZ3e/dDdEdFZ4dNe e/ej5fe e e/ej5fe6e e6e e e/e/fe e e6e/fe e/e6e/dI dJdKZ7GdLdMdMZ8dS(OzAuto Tokenizer class.N) OrderedDict) TYPE_CHECKINGDictOptionalTupleUnion)PretrainedConfig)get_class_from_dynamic_moduleresolve_trust_remote_code)load_gguf_checkpoint)PreTrainedTokenizer)TOKENIZER_CONFIG_FILE) cached_fileextract_commit_hashis_g2p_en_availableis_sentencepiece_availableis_tokenizers_availablelogging)EncoderDecoderConfig)_LazyAutoMapping)CONFIG_MAPPING_NAMES AutoConfigconfig_class_to_model_typemodel_type_to_module_name!replace_list_option_in_docstrings)PreTrainedTokenizerFastTOKENIZER_MAPPING_NAMESZalbertZAlbertTokenizerZAlbertTokenizerFastZalignZ BertTokenizerZBertTokenizerFastZbark)Zbart)Z BartTokenizerZBartTokenizerFastZbarthezZBarthezTokenizerZBarthezTokenizerFast)Zbartpho)ZBartphoTokenizerNZbertzbert-generationZBertGenerationTokenizer)z bert-japanese)ZBertJapaneseTokenizerN)Zbertweet)ZBertweetTokenizerNZbig_birdZBigBirdTokenizerZBigBirdTokenizerFastZbigbird_pegasusZPegasusTokenizerZPegasusTokenizerFast)Zbiogpt)ZBioGptTokenizerN)Z blenderbot)ZBlenderbotTokenizerZBlenderbotTokenizerFast)zblenderbot-small)ZBlenderbotSmallTokenizerNZblipzblip-2Z GPT2TokenizerZGPT2TokenizerFastZbloomZBloomTokenizerFastZ bridgetowerZRobertaTokenizerZRobertaTokenizerFastZbros)Zbyt5)Z ByT5TokenizerNZ camembertZCamembertTokenizerZCamembertTokenizerFast)Zcanine)ZCanineTokenizerNZ chameleonZLlamaTokenizerZLlamaTokenizerFastZ chinese_clipZclapZclipZ CLIPTokenizerZCLIPTokenizerFastZclipseg)Zclvp)Z ClvpTokenizerNZ code_llamaZCodeLlamaTokenizerZCodeLlamaTokenizerFastZcodegenZCodeGenTokenizerZCodeGenTokenizerFastZcohereZCohereTokenizerFastZconvbertZConvBertTokenizerZConvBertTokenizerFastZcpmZ CpmTokenizerZCpmTokenizerFast)Zcpmant)ZCpmAntTokenizerN)Zctrl)Z CTRLTokenizerN)zdata2vec-audioZWav2Vec2CTCTokenizerNz data2vec-textZdbrxZdebertaZDebertaTokenizerZDebertaTokenizerFastz deberta-v2ZDebertaV2TokenizerZDebertaV2TokenizerFastZ distilbertZDistilBertTokenizerZDistilBertTokenizerFastZdprZDPRQuestionEncoderTokenizerZDPRQuestionEncoderTokenizerFastZelectraZElectraTokenizerZElectraTokenizerFastZernieZernie_mZErnieMTokenizer)Zesm)Z EsmTokenizerNZfalconrZfastspeech2_conformerZFastSpeech2ConformerTokenizer)Zflaubert)ZFlaubertTokenizerNZfnetZ FNetTokenizerZFNetTokenizerFast)Zfsmt)Z FSMTTokenizerNZfunnelZFunnelTokenizerZFunnelTokenizerFastZgemmaZGemmaTokenizerZGemmaTokenizerFastZgemma2gitzgpt-sw3ZGPTSw3TokenizerZgpt2Z gpt_bigcodeZgpt_neoZgpt_neoxZGPTNeoXTokenizerFast)Zgpt_neox_japanese)ZGPTNeoXJapaneseTokenizerNZgptj)zgptsan-japanese)ZGPTSanJapaneseTokenizerNzgrounding-dinoZgroupvitZherbertZHerbertTokenizerZHerbertTokenizerFast)Zhubertr ZibertZideficsZidefics2Z instructblipZinstructblipvideoZjambaZjetmoe)Zjukebox)ZJukeboxTokenizerNzkosmos-2ZXLMRobertaTokenizerZXLMRobertaTokenizerFastZlayoutlmZLayoutLMTokenizerZLayoutLMTokenizerFastZ layoutlmv2ZLayoutLMv2TokenizerZLayoutLMv2TokenizerFastZ layoutlmv3ZLayoutLMv3TokenizerZLayoutLMv3TokenizerFastZ layoutxlmZLayoutXLMTokenizerZLayoutXLMTokenizerFastZledZ LEDTokenizerZLEDTokenizerFastZliltZllamaZllavazllava-next-videoZ llava_nextZ longformerZLongformerTokenizerZLongformerTokenizerFastZlongt5Z T5TokenizerZT5TokenizerFast)Zluke)Z LukeTokenizerNZlxmertZLxmertTokenizerZLxmertTokenizerFastZm2m_100ZM2M100TokenizerZmambaZmamba2ZmarianZMarianTokenizerZmbartZMBartTokenizerZMBartTokenizerFastZmbart50ZMBart50TokenizerZMBart50TokenizerFastZmegaz megatron-bert)zmgp-str)ZMgpstrTokenizerNZmistralZmixtralZmlukeZMLukeTokenizerZ mobilebertZMobileBertTokenizerZMobileBertTokenizerFastZmpnetZMPNetTokenizerZMPNetTokenizerFastZmptZmraZmt5Z MT5TokenizerZMT5TokenizerFastZmusicgenZmusicgen_melodyZmvpZ MvpTokenizerZMvpTokenizerFastZnezhaZnllbZ NllbTokenizerZNllbTokenizerFastznllb-moeZ nystromformerZolmoZ oneformerz openai-gptZOpenAIGPTTokenizerZOpenAIGPTTokenizerFastoptZowlv2ZowlvitZ paligemmaZpegasusZ pegasus_x)Z perceiver)ZPerceiverTokenizerNZ persimmonphiZphi3)Zphobert)ZPhobertTokenizerNZ pix2structZplbartZPLBartTokenizer)Z prophetnet)ZProphetNetTokenizerNZqdqbertZqwen2ZQwen2TokenizerZQwen2TokenizerFastZ qwen2_moe)Zrag)Z RagTokenizerNrealmZRealmTokenizerZRealmTokenizerFastZrecurrent_gemmaZreformerZReformerTokenizerZReformerTokenizerFastZrembertZRemBertTokenizerZRemBertTokenizerFastZ retribertZRetriBertTokenizerZRetriBertTokenizerFastZrobertazroberta-prelayernorm)Zroc_bert)ZRoCBertTokenizerNZroformerZRoFormerTokenizerZRoFormerTokenizerFastZrwkvZ seamless_m4tZSeamlessM4TTokenizerZSeamlessM4TTokenizerFastZseamless_m4t_v2ZsiglipZSiglipTokenizerZspeech_to_textZSpeech2TextTokenizer)Zspeech_to_text_2)ZSpeech2Text2TokenizerNZspeecht5ZSpeechT5Tokenizer)Zsplinter)ZSplinterTokenizerZSplinterTokenizerFastZ squeezebertZSqueezeBertTokenizerZSqueezeBertTokenizerFastZstablelmZ starcoder2Zswitch_transformersZt5)Ztapas)ZTapasTokenizerN)Ztapex)ZTapexTokenizerN)z transfo-xl)ZTransfoXLTokenizerNZtvpZudopZ UdopTokenizerZUdopTokenizerFastZumt5Z video_llavaZviltZvipllavaZ visual_bert)Zvits)Z VitsTokenizerN)Zwav2vec2r )z wav2vec2-bertr )zwav2vec2-conformerr )Zwav2vec2_phoneme)ZWav2Vec2PhonemeCTCTokenizerNZwhisperZWhisperTokenizerZWhisperTokenizerFastZxclipZxglmZ XGLMTokenizerZXGLMTokenizerFast)Zxlm)Z XLMTokenizerNzxlm-prophetnetZXLMProphetNetTokenizerz xlm-robertazxlm-roberta-xlZxlnetZXLNetTokenizerZXLNetTokenizerFastZxmodZyosocCsi|]\}}||qSr%).0kvr%r%N/tmp/pip-unpacked-wheel-zw5xktn0/transformers/models/auto/tokenization_auto.py 'sr*) 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 tokenizersmoduleconfig tokenizerZ main_moduler%r%r)tokenizer_class_from_name*s$    r:F) pretrained_model_name_or_path cache_dirforce_downloadresume_downloadproxiestokenrevisionlocal_files_only subfolderc Ks| dd} | dk r4tdt|dk r0td| }| dd} t|t||||||||ddd| d} | dkrzt 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. - 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: 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. 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("google-bert/bert-base-uncased") # This model does not have a tokenizer config so the result will be an empty dict. tokenizer_config = get_tokenizer_config("FacebookAI/xlm-roberta-base") # Save a pretrained tokenizer locally and you can reload its config from transformers import AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("google-bert/bert-base-cased") tokenizer.save_pretrained("tokenizer-test") tokenizer_config = get_tokenizer_config("tokenizer-test") ```use_auth_tokenNrThe `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.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_gated_repoZ%_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 ValueErrorgetrrloggerinforopenjsonload)r<r=r>r?r@rArBrCrDkwargsrEZ commit_hashZresolved_config_filereaderresultr%r%r)get_tokenizer_configFsDI    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__szAutoTokenizer.__init__c OsL|dd}|dk r@tdt|dddk r8td||d<|dd}d|d<|d d}|d d}|d d}|d d} |dk r6d} t|d} | dkrtd |ddddtDd| \} } |r| dk rt | } n t d| dkr t | } | dkr$td| d| j |f||St |f|}d|krX|d|d<|d}d}d|krt|dttfr|d}n|ddd}|dkr$t|ts| rt|| f|}t|ddd}tjf|}ntj |fd |i|}|j}t|dr$d|jkr$|jd}|dk }t|tkp`|dk o`t |dk p`t |ddk }t||||}|r|r|r|ddk r|d}n|d}t||f|} |dd}tj|r| | j |f|d |i|S|dk r`d} |r|!ds|d}t |} | dkr4|}t |} | dkrNtd|d | j |f||St|t"rt|j#t|j$k rt d!|j$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)(a] 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) ```rENrFrArGr8TZ _from_autouse_fasttokenizer_typetrust_remote_code gguf_filezPassed `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_maprYF)Zreturn_tensorsZFastrrZ code_revisionz- 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|] }|jVqdSra)r-rbr%r%r)rds)(rJrKrLrMrOrNrjoinkeysr:rPwarningfrom_pretrainedrX isinstancetuplelistr rr rZ for_modelrer5rftyper3r r ospathisdirZregister_for_auto_classendswithrdecoderencoder __class__rr-)clsr<inputsrUrEr8r]r^r_r`reZtokenizer_class_tupleZtokenizer_class_nameZtokenizer_fast_class_nameZtokenizer_configZconfig_tokenizer_classZtokenizer_auto_mapZ gguf_pathZ config_dictZhas_remote_codeZhas_local_codeZ class_ref_Ztokenizer_class_candidateZ model_typeZtokenizer_class_pyZtokenizer_class_fastr%r%r)rjsM        $                        &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_classr3r4register)Z config_classr{Zfast_tokenizer_classryZ existing_slowZ existing_fastr%r%r)r|s0   zAutoTokenizer.register)NNF) r- __module__ __qualname____doc__r\ classmethodrrrjr|r%r%r%r)rYs _rY)NFNNNNFr;)9rr/rSrorK collectionsrtypingrrrrrZconfiguration_utilsr Zdynamic_module_utilsr r Zmodeling_gguf_pytorch_utilsr Ztokenization_utilsr Ztokenization_utils_baserutilsrrrrrrZencoder_decoderrZ auto_factoryrZconfiguration_autorrrrrZtokenization_utils_fastrZ get_loggerr-rPrstr__annotations__r3r.ZCONFIG_TO_TYPEr:PathLikeboolrXrYr%r%r%r)s`          *k  o