o wiB@sldZddlZddlZddlZddlZddlmZddlmZm Z m Z ddl m Z ddl mZmZddlmZdd lmZdd lmZdd lmZmZmZmZmZmZd d lmZddlm Z ddl!m"Z"m#Z#m$Z$m%Z%m&Z&ervddl'm(Z(ndZ(e)e*Z+ee,e-e e,e e,ffgderdnderdndffdderdndffdderdndffdderdndffdderdndffdderdndffdd erd!nderd"ndffd#d$derdndffd%erd&nddffd'd(d)erd*nderd+ndffd,d-erd.ndffd/d0der(d1ndffd2d3d4der8dndffd5d6erDd7ndffd8derPd9ndffd:d;er\dd?erud@nder|dAndffdBdCerdnderdndffdDderdndffdEd;erddndffderIdnderPdndffder[dnderbdndffdermdndertdndffderdnderdndffdderdndffdderd1ndffdderd1ndffdderd1ndffderdnddffdd6erd7ndffdd6erd7ndffdd6erd7ndffdderd{ndffddd6erd7ndffddddddderdndffddGer"dHndffdder.d1ndffdder:dndffddd;erHdndffd?e rd=nde rd>ndffd@e rdnde rdndffdAe rdBnddffdCe rdnde rdndffdDde rd1ndffdEe rdFnddffdGdHe rdInddffdJdKdLe rdMndffdNde rd{ndffdOd6e r"d7ndffdPe r.dnde r5dndffdQe rAdnde rHdndffdRe rTdnde r[dndffdSdTdUdVde rqdndffdWe r~dXnde rdYndffdZe rdnde rdndffd[de rdndffd\de rdndffd]de rdndffd^de rdndffd_d`dadbdcdddee rdfndffdgdGe rdHndffdhe rdinde r djndffdkdle rdmnddffdne r*dnde r1dndffdoe r=dnde rDdndffdpe rQdqnde rYdrndffdse rednde rldndffdte rxdnde rdndffdue rdnde rdndffdve rdnde rdndffZ.e e"e.Z/dwdxe"0DZ1dye,dze e2edffd{d|Z3  }     } ~dde e,ej4e,fde e e,ej4e,fde5de e5de e6e,e,fde e e5e,fde e,de5de,dze6e,effddZ7GdddZ8ddgZ9dS(zAuto Tokenizer class.N) OrderedDict)AnyOptionalUnion)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)PreTrainedTokenizerFastalbertAlbertTokenizerAlbertTokenizerFastalign BertTokenizerBertTokenizerFastarceeLlamaTokenizerLlamaTokenizerFastaria aya_visionCohereTokenizerFastbark)bart) BartTokenizerBartTokenizerFastbarthezBarthezTokenizerBarthezTokenizerFast)bartpho)BartphoTokenizerNbertzbert-generationBertGenerationTokenizer)z bert-japanese)BertJapaneseTokenizerN)bertweet)BertweetTokenizerNbig_birdBigBirdTokenizerBigBirdTokenizerFastbigbird_pegasusPegasusTokenizerPegasusTokenizerFast)biogpt)BioGptTokenizerNbitnetr) blenderbot)BlenderbotTokenizerBlenderbotTokenizerFast)zblenderbot-small)BlenderbotSmallTokenizerNblipzblip-2 GPT2TokenizerGPT2TokenizerFastbloomBloomTokenizerFast bridgetowerRobertaTokenizerRobertaTokenizerFastbros)byt5) ByT5TokenizerN camembertCamembertTokenizerCamembertTokenizerFast)canine)CanineTokenizerN chameleon chinese_clipclapclip CLIPTokenizerCLIPTokenizerFastclipseg)clvp) ClvpTokenizerN code_llamaCodeLlamaTokenizerCodeLlamaTokenizerFastcodegenCodeGenTokenizerCodeGenTokenizerFastcoherecohere2colpalicolqwen2Qwen2TokenizerQwen2TokenizerFastconvbertConvBertTokenizerConvBertTokenizerFastcpm CpmTokenizerCpmTokenizerFast)cpmant)CpmAntTokenizerN)ctrl) CTRLTokenizerN)zdata2vec-audioWav2Vec2CTCTokenizerNz data2vec-textdbrxdebertaDebertaTokenizerDebertaTokenizerFastz deberta-v2DebertaV2TokenizerDebertaV2TokenizerFast deepseek_v3)dia) DiaTokenizerN diffllama distilbertDistilBertTokenizerDistilBertTokenizerFastdprDPRQuestionEncoderTokenizerDPRQuestionEncoderTokenizerFastelectraElectraTokenizerElectraTokenizerFastemu3ernieernie_mErnieMTokenizer)esm) EsmTokenizerNfalcon falcon_mambaGPTNeoXTokenizerFastfastspeech2_conformerFastSpeech2ConformerTokenizer)flaubert)FlaubertTokenizerNfnet FNetTokenizerFNetTokenizerFast)fsmt) FSMTTokenizerNfunnelFunnelTokenizerFunnelTokenizerFastgemmaGemmaTokenizerGemmaTokenizerFastgemma2gemma3 gemma3_textgemma3n gemma3n_textgitglmglm4glm4vzgpt-sw3GPTSw3Tokenizergpt2 gpt_bigcodegpt_neogpt_neox)gpt_neox_japanese)GPTNeoXJapaneseTokenizerNgptj)zgptsan-japanese)GPTSanJapaneseTokenizerN)graniterEN) granitemoer)granitemoehybridr)granitemoesharedrzgrounding-dinogroupvitheliumherbertHerbertTokenizerHerbertTokenizerFast)hubertrsibertideficsidefics2idefics3 instructblipinstructblipvideointernvljambajanusjetmoe)jukebox)JukeboxTokenizerNzkosmos-2XLMRobertaTokenizerXLMRobertaTokenizerFastlayoutlmLayoutLMTokenizerLayoutLMTokenizerFast layoutlmv2LayoutLMv2TokenizerLayoutLMv2TokenizerFast layoutlmv3LayoutLMv3TokenizerLayoutLMv3TokenizerFast layoutxlmLayoutXLMTokenizerLayoutXLMTokenizerFastled LEDTokenizerLEDTokenizerFastliltllamallama4 llama4_textllava llava_nextllava_next_videollava_onevision longformerLongformerTokenizerLongformerTokenizerFastlongt5 T5TokenizerT5TokenizerFast)luke) LukeTokenizerNlxmertLxmertTokenizerLxmertTokenizerFastm2m_100M2M100Tokenizermambamamba2marianMarianTokenizermbartMBartTokenizerMBartTokenizerFastmbart50MBart50TokenizerMBart50TokenizerFastmegaz megatron-bert)zmgp-str)MgpstrTokenizerNminimaxmistralmixtralmllamamlukeMLukeTokenizer mobilebertMobileBertTokenizerMobileBertTokenizerFast modernbert moonshinemoshimpnetMPNetTokenizerMPNetTokenizerFastmptmramt5 MT5TokenizerMT5TokenizerFastmusicgenmusicgen_melodymvp MvpTokenizerMvpTokenizerFast)myt5) MyT5TokenizerNnemotronnezhanllb NllbTokenizerNllbTokenizerFastznllb-moe nystromformerolmoolmo2olmoez omdet-turbo oneformerz openai-gptOpenAIGPTTokenizerOpenAIGPTTokenizerFastoptowlv2owlvit paligemmapegasus pegasus_x) perceiver)PerceiverTokenizerN persimmonphiphi3phimoe)phobert)PhobertTokenizerN pix2structpixtralplbartPLBartTokenizer) prophetnet)ProphetNetTokenizerNqdqbertqwen2 qwen2_5_omni qwen2_5_vl qwen2_audio qwen2_moeqwen2_vlqwen3 qwen3_moe)rag) RagTokenizerNrealmRealmTokenizerRealmTokenizerFastrecurrent_gemmareformerReformerTokenizerReformerTokenizerFastrembertRemBertTokenizerRemBertTokenizerFast retribertRetriBertTokenizerRetriBertTokenizerFastrobertazroberta-prelayernorm)roc_bert)RoCBertTokenizerNroformerRoFormerTokenizerRoFormerTokenizerFastrwkv seamless_m4tSeamlessM4TTokenizerSeamlessM4TTokenizerFastseamless_m4t_v2 shieldgemma2siglipSiglipTokenizersiglip2smollm3speech_to_textSpeech2TextTokenizer)speech_to_text_2)Speech2Text2TokenizerNspeecht5SpeechT5Tokenizer)splinter)SplinterTokenizerSplinterTokenizerFast squeezebertSqueezeBertTokenizerSqueezeBertTokenizerFaststablelm starcoder2switch_transformerst5t5gemma)tapas)TapasTokenizerN)tapex)TapexTokenizerN)z transfo-xl)TransfoXLTokenizerNtvpudop UdopTokenizerUdopTokenizerFastumt5 video_llavaviltvipllava visual_bert)vits) VitsTokenizerN)wav2vec2rs)z wav2vec2-bertrs)zwav2vec2-conformerrs)wav2vec2_phoneme)Wav2Vec2PhonemeCTCTokenizerNwhisperWhisperTokenizerWhisperTokenizerFastxclipxglm XGLMTokenizerXGLMTokenizerFast)xlm) XLMTokenizerNzxlm-prophetnetXLMProphetNetTokenizerz xlm-robertazxlm-roberta-xlxlnetXLNetTokenizerXLNetTokenizerFastxmodyosozambazamba2cCsi|]\}}||qSr).0kvrrg/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py sr class_namereturnc Cs|dkrtStD]'\}}||vr1t|}td|d}zt||WSty0Yq wq tj D]\}}|D]}t|dd|krM|Sq=q7td}t ||r^t||SdS)Nr.ztransformers.models__name__ transformers) rTOKENIZER_MAPPING_NAMESitemsr importlib import_modulegetattrAttributeErrorTOKENIZER_MAPPING_extra_contenthasattr)r module_name tokenizersmoduleconfig tokenizer main_modulerrrtokenizer_class_from_names,      rFpretrained_model_name_or_path cache_dirforce_downloadresume_downloadproxiestokenrevisionlocal_files_only subfolderc Ks| dd} | durtdt|durtd| }| dd} t|t||||||||ddd| d} | dur=t diSt | | } t | d d  } t | }Wdn1sXwY| |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) rrrrrrrr _raise_exceptions_for_gated_repo%_raise_exceptions_for_missing_entries'_raise_exceptions_for_connection_errorsrz\Could not locate the tokenizer configuration file, will try to use the model config instead.zutf-8)encoding)popwarningswarn FutureWarning ValueErrorgetr r loggerinforopenjsonload)rrrrrrrrrkwargsr commit_hashresolved_config_filereaderresultrrrget_tokenizer_configsF I    rc@s:eZdZdZddZeeeddZe d 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). cCstd)Nz}AutoTokenizer is designed to be instantiated using the `AutoTokenizer.from_pretrained(pretrained_model_name_or_path)` method.)OSError)selfrrr__init__RszAutoTokenizer.__init__c Osz|dd}|dur tdt|dddurtd||d<|dd}d|d<|d d}|d d}|d d}|d d} |durd} t|d} | durgtd |ddddtDd| \} } |r{| durvt | } nt d| durt | } | durtd| d| j |g|Ri|St |fi|}d|vr|d|d<|d}d}d|vrt|dttfr|d}n|ddd}|durt|ts| rt|| fi|}t|ddd}tjd)i|}n tj |fd |i|}|j}t|drd|jvr|jd}|du}t|tvp1|duo1t |dup1t |ddu}|r_|rD|ddurD|d}n|d}d|vrU|dd}nd}t|||||}|r|rt||fi|} |d d}| | j |g|Rd |i|S|durd} |r|ds|d}t |} | dur|}t |} | durtd|d!| j |g|Ri|St|t rt|j!t|j"urt d"|j"j#d#|j!j#d$|j"}t$t|j%}|dur'tt|\}}|r|s|dur|j |g|Ri|S|dur#|j |g|Ri|Std%td&|j#d'dd(dtDd)*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) ```rNrrrrT _from_autouse_fasttokenizer_typetrust_remote_code gguf_filezPassed `tokenizer_type` z3 does not exist. `tokenizer_type` should be one of z, css|]}|VqdSNrrcrrr sz0AutoTokenizer.from_pretrained..rzt`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.rtokenizer_classauto_maprF)return_tensorsFastrrz-- 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|]}|jVqdSr)rrrrrr9sr)&rrrrrrrjoinkeysrrwarningfrom_pretrainedr isinstancetuplelistrr r r for_modelrrrtypersplitr rregister_for_auto_classendswithrdecoderencoder __class__rr)clsrinputsrrrrrrrrtokenizer_class_tupletokenizer_class_nametokenizer_fast_class_nametokenizer_configconfig_tokenizer_classtokenizer_auto_map gguf_path config_dicthas_remote_codehas_local_code class_ref upstream_repo_tokenizer_class_candidate model_typetokenizer_class_pytokenizer_class_fastrrrrXs M                             zAutoTokenizer.from_pretrainedNFcCs|dur |dur td|durt|trtd|dur&t|tr&td|durD|durDt|trD|j|krDtd|jd|d|tjvr[t|\}}|durU|}|dur[|}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)r issubclassrr slow_tokenizer_classrrregister) config_classrfast_tokenizer_classr existing_slow existing_fastrrrr<s2   zAutoTokenizer.register)NNF) r __module__ __qualname____doc__r classmethodrrr staticmethodrrrrrrJs crr)NFNNNNFr):rrrosr collectionsrtypingrrrconfiguration_utilsrdynamic_module_utilsrr modeling_gguf_pytorch_utilsr tokenization_utilsr tokenization_utils_baser utilsr rrrrrencoder_decoderr auto_factoryrconfiguration_autorrrrrtokenization_utils_fastr get_loggerrrstrrrrrCONFIG_TO_TYPErrPathLikebooldictrr__all__rrrrs                    !"#$%&'()*+-35;=DKQSYZ[\]^`fghijkmtz|   ")07>DEFGHIJKLMNOPQRSTUVWXYZ[\]^_agioqwxyz{|~  !"#$&-3457>EKLMNOPQRSU[\]^_`bipvwxz}#$%&'()*+-3457=?FLMOV]cdfijkmt{    $*+,-/6<=>?@ABCDEFHNOQX_fmt{ &  o!