qivdZddlZddlmZddlmZej eZddiZ dZ Gd d eZ d gZ y) zTokenization classes for ESM.N)PreTrainedTokenizer)logging vocab_file vocab.txtct|d5}|jj}|Dcgc]}|jc}cdddScc}w#1swYyxYw)Nr)openread splitlinesstrip)rflinesls Z/opt/pipecat/venv/lib/python3.12/site-packages/transformers/models/esm/tokenization_esm.pyload_vocab_filersS j# *!##%#()a )**)**s#AAAAA!c eZdZdZeZddgZ dfd Zdede fdZ de defd Z d Z d Z de defd Zdede fd Z ddeedeedzdeefdZ ddededzdedeefdZdZedefdZxZS) EsmTokenizerz& Constructs an ESM tokenizer. input_idsattention_maskc Vt||_tt|j|_t|jD cic]\}} | | c} }|_t |d|||||d||j|_|j|jycc} }w)N) unk_token cls_token pad_token mask_token eos_token) r all_tokensdict enumerate _id_to_token _token_to_idsuper__init__unique_no_split_tokens _update_trie) selfrrrrrrkwargsindtok __class__s rr$zEsmTokenizer.__init__)s**5 4??!;<6?6PQ(#sS#XQ  !    '+oo# $556Rs B%indexreturncN|jj||jSNr!getrr'r,s r_convert_id_to_tokenz!EsmTokenizer._convert_id_to_tokenE  $$UDNN;;tokenc|jj||jj|jSr/r"r1rr'r6s r_convert_token_to_idz!EsmTokenizer._convert_token_to_idH0  $$UD,=,=,A,A$..,QRRr5c "|jSr/)split)r'textr(s r _tokenizezEsmTokenizer._tokenizeKszz|r5cp|jj}|j|j|Sr/)r"copyupdateadded_tokens_encoder)r' base_vocabs r get_vocabzEsmTokenizer.get_vocabNs0&&++- $334r5c|jj||jj|jSr/r8r9s r token_to_idzEsmTokenizer.token_to_idSr;r5cN|jj||jSr/r0r2s r id_to_tokenzEsmTokenizer.id_to_tokenVr4r5N token_ids_0 token_ids_1c|jg}|jg}||j||zS||z|zS|j td||z|z|z|zS)Nz=Cannot tokenize multiple sequences when EOS token is not set!) cls_token_id eos_token_id ValueError)r'rJrKclsseps r build_inputs_with_special_tokensz-EsmTokenizer.build_inputs_with_special_tokensYs  !  !    ([(([(3..    &\] ][ 3&4s::r5already_has_special_tokensc|r-| td|Dcgc]}||jvrdndc}Sdgdgt|zzdgz}||dgt|zdgzz }|Scc}w)a 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. zYou should not supply a second sequence if the provided sequence of ids is already formatted with special tokens for the model.r)rOall_special_idslen)r'rJrKrSr6masks rget_special_tokens_maskz$EsmTokenizer.get_special_tokens_maskgs$ && R LWW%$"6"66AA=W WsqcC ,,-3  " QC#k**aS0 0D XsA!ctjj||r|dznddz}t|d5}|j dj|j ddd|fS#1swY|fSxYw)N-rw )ospathjoinr writer)r'save_directoryfilename_prefixrrs rsave_vocabularyzEsmTokenizer.save_vocabularyskWW\\.O?S3Hacgr2rs *c " 0a GGDIIdoo. / 0} 0}s +A--A8c,t|jSr/)rWr)r's r vocab_sizezEsmTokenizer.vocab_sizes4??##r5)zzzzzr/)NF)__name__ __module__ __qualname____doc__VOCAB_FILES_NAMESvocab_files_namesmodel_input_namesr$intstrr3r:r?rErGrIlistrRboolrYrepropertyrg __classcell__)r+s@rrr!s*$&67 78<#<#<S#S#S SSS<<<GK ;9 ;379t3C ; c ;fk.2Tk^b c> $C$$r5r) rkr_tokenization_pythonrutilsr get_loggerrhloggerrlrr__all__rr5rrzsQ$ 6   H %!;/* m$&m$`  r5