o ei@sXdZddlZddlmZddlmZeeZddiZ dd Z Gd d d eZ d gZ dS) zTokenization classes for ESM.N)PreTrainedTokenizer)logging vocab_file vocab.txtcCsHt|d}|}dd|DWdS1swYdS)NrcSsg|]}|qS)strip).0lrrf/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/esm/tokenization_esm.py sz#load_vocab_file..)openread splitlines)rflinesrrr load_vocab_files   $rc seZdZdZeZddgZ     d'fd d Zd ed e fd dZ de d efddZ ddZ ddZ de d efddZd ed e fddZ d(deedeedBd eefddZ d)dededBd ed eefd!d"Zd#d$Zed efd%d&ZZS)* EsmTokenizerz& Constructs an ESM tokenizer. input_idsattention_maskc sft||_tt|j|_ddt|jD|_tjd|||||d||j|_| |jdS)NcSsi|]\}}||qSrr)r indtokrrr 5sz)EsmTokenizer.__init__..) unk_token cls_token pad_token mask_token eos_tokenr) r all_tokensdict enumerate _id_to_token _token_to_idsuper__init__unique_no_split_tokens _update_trie)selfrrr r!r"r#kwargs __class__rr r*)s  zEsmTokenizer.__init__indexreturncC|j||jSNr'getrr-r1rrr _convert_id_to_tokenEz!EsmTokenizer._convert_id_to_tokentokencC|j||j|jSr4r(r6rr-r:rrr _convert_token_to_idHz!EsmTokenizer._convert_token_to_idcKs|Sr4)split)r-textr.rrr _tokenizeKszEsmTokenizer._tokenizecCs|j}||j|Sr4)r(copyupdateadded_tokens_encoder)r- base_vocabrrr get_vocabNs  zEsmTokenizer.get_vocabcCr;r4r<r=rrr token_to_idSr?zEsmTokenizer.token_to_idcCr3r4r5r7rrr id_to_tokenVr9zEsmTokenizer.id_to_tokenN token_ids_0 token_ids_1cCs\|jg}|jg}|dur|jdur||S|||S|jdur$td|||||S)Nz=Cannot tokenize multiple sequences when EOS token is not set!) cls_token_id eos_token_id ValueError)r-rJrKclsseprrr build_inputs_with_special_tokensYs   z-EsmTokenizer.build_inputs_with_special_tokensFalready_has_special_tokenscsd|r|dur tdfdd|DSdgdgt|dg}|dur0|dgt|dg7}|S)a Retrieves sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the tokenizer `prepare_for_model` or `encode_plus` methods. Args: token_ids_0 (`list[int]`): List of ids of the first sequence. token_ids_1 (`list[int]`, *optional*): List of ids of the second sequence. already_has_special_tokens (`bool`, *optional*, defaults to `False`): Whether or not the token list is already formatted with special tokens for the model. Returns: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token. NzYou should not supply a second sequence if the provided sequence of ids is already formatted with special tokens for the model.csg|] }|jvr dndqS)r)all_special_ids)r r:r-rr r sz8EsmTokenizer.get_special_tokens_mask..rSr)rNlen)r-rJrKrRmaskrrUr get_special_tokens_maskgsz$EsmTokenizer.get_special_tokens_maskcCsdtj||r |dndd}t|d}|d|jWd|fS1s*wY|fS)N-rw )ospathjoinrwriter$)r-save_directoryfilename_prefixrrrrr save_vocabularys  zEsmTokenizer.save_vocabularycCs t|jSr4)rVr$rUrrr vocab_sizes zEsmTokenizer.vocab_size)rrrrrr4)NF)__name__ __module__ __qualname____doc__VOCAB_FILES_NAMESvocab_files_namesmodel_input_namesr*intstrr8r>rBrGrHrIlistrQboolrXrcpropertyrd __classcell__rrr/r r!sJ   r) rhr]tokenization_pythonrutilsr get_loggerreloggerrirr__all__rrrr s     p