cCi"SrSSKrSSKJrJr SSKJr SSKJr SSK J r J r J r SSK JrJrJr SS KJr S S KJr \R*"\5r"S S \ SS9r"SS\ 5rS/rg)zq Processor class for InstructBLIP. Largely copy of Blip2Processor with addition of a tokenizer for the Q-Former. N)OptionalUnion) BatchFeature) ImageInput)ProcessingKwargsProcessorMixinUnpack) AddedTokenPreTokenizedInput TextInput)logging) AutoTokenizerc 2\rSrSrSSSSSSSSSS. 0S.rSrg) InstructBlipProcessorKwargs!TFr) add_special_tokenspaddingstridereturn_overflowing_tokensreturn_special_tokens_maskreturn_offsets_mappingreturn_token_type_ids return_lengthverbose) text_kwargs images_kwargsN)__name__ __module__ __qualname____firstlineno__ _defaults__static_attributes__rr/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/instructblip/processing_instructblip.pyrr!s0#').*/&+%*"   Ir&rF)totalc ^\rSrSrSr/SQrSrSrSrSU4Sjjr SS\ \ S\ \ \\\ \\4S \\S \4S jjr\S 5rU4S jr\U4Sj5rSrU=r$)InstructBlipProcessor2aX Constructs an InstructBLIP processor which wraps a BLIP image processor and a LLaMa/T5 tokenizer into a single processor. [`InstructBlipProcessor`] offers all the functionalities of [`BlipImageProcessor`] and [`AutoTokenizer`]. See the docstring of [`~BlipProcessor.__call__`] and [`~BlipProcessor.decode`] for more information. Args: image_processor (`BlipImageProcessor`): An instance of [`BlipImageProcessor`]. The image processor is a required input. tokenizer (`AutoTokenizer`): An instance of ['PreTrainedTokenizer`]. The tokenizer is a required input. qformer_tokenizer (`AutoTokenizer`): An instance of ['PreTrainedTokenizer`]. The Q-Former tokenizer is a required input. num_query_tokens (`int`, *optional*):" Number of tokens used by the Qformer as queries, should be same as in model's config. )image_processor tokenizerqformer_tokenizer)BlipImageProcessorBlipImageProcessorFastrc >[US5(d,[SSSS9UlURUR/SS9 OURUlX@l[ TU]XU5 g)N image_tokenzFT) normalizedspecial)special_tokens)hasattrr r2 add_tokensnum_query_tokenssuper__init__)selfr,r-r.r8kwargs __class__s r'r:InstructBlipProcessor.__init__Jsay-00))tTD   $"2"2!3D I(44D  0 5FGr&imagestextr<returnc UcUc [S5eUR"[4SURR0UD6nUSR SS5n0nUGb^[ U[5(aU/nO8[ U[5(d#[ US[5(d [S5eUR"U40USD6n U R S5US 'U R S 5US 'USRS 5bUSS ==UR-ss'UR"U40USD6n UbvURRUR-n S USS'S USS'S USS'UR"U 40USD6n U Hn XVs/sH oU U-PM snX'M! URU 5 Ub'UR"U40USD6nURU5 [!XS9nU$s snf)aP This method uses [`BlipImageProcessor.__call__`] method to prepare image(s) for the model, and [`BertTokenizerFast.__call__`] to prepare text for the model. Please refer to the docstring of the above two methods for more information. Args: images (`ImageInput`): The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch tensor. Both channels-first and channels-last formats are supported. text (`TextInput`, `PreTokenizedInput`, `list[TextInput]`, `list[PreTokenizedInput]`): The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set `is_split_into_words=True` (to lift the ambiguity with a batch of sequences). Nz,You have to specify at least images or text.tokenizer_init_kwargsrreturn_tensorsrzAInvalid input text. Please provide a string, or a list of strings input_idsqformer_input_idsattention_maskqformer_attention_mask max_lengthFrr truncationr) tensor_type) ValueError _merge_kwargsrr- init_kwargspop isinstancestrlistr.getr8r2contentupdater,r)r;r?r@audiovideosr< output_kwargsrDencodingqformer_text_encoding text_encoding image_tokensimage_text_encodingksampleimage_encodings r'__call__InstructBlipProcessor.__call__Ts%, >dlKL L** ' "&.."<"<  '}599:JDQ  $$$vd++JtAw4L4L !dee$($:$:4$`=Q^C_$` !,A,E,Ek,RH( )1F1J1JK[1\H- .]+// =Im,\:d>S>SS: NN4P=3OPM!#//77$:O:OO EJ m,-AB:? m,Y7=B m,\:&*nn\&b]S`Ea&b#&AVcVf'gVfFA(>(GVf'gM$' OOM *  !11&[M/[RRU5(a[SUS35e[R"USS9 [RR US5nUR RU5 SUR;nU(aURRS5 [TU]"U40UD6nU(aU=RS/- slU$)NzProvided path (z#) should be a directory, not a fileT)exist_okr.) ospathisfilerLmakedirsjoinr.save_pretrained attributesremover9)r;save_directoryr<qformer_tokenizer_pathqformer_presentoutputsr=s r'rp%InstructBlipProcessor.save_pretraineds 77>>. ) )~.>>abc c NT2!#n>Q!R ../EF.@  OO " "#6 7').CFC  OO 34 4Or&c >[TU]"U40UD6n[U[5(aUSn[R"USS9nXClU$)Nrr.) subfolder)r9from_pretrainedrPtuplerr.)clspretrained_model_name_or_pathr< processorr.r=s r'rz%InstructBlipProcessor.from_pretrainedsQG+,ITVT  i ' '!! I)99:Wcvw&7#r&)r2r8)N)NNNN)r r!r"r#__doc__rqimage_processor_classtokenizer_classqformer_tokenizer_classr:rrrr r rRr rrrapropertyrdrp classmethodrzr% __classcell__)r=s@r'r*r*2s$GJL%O-H(,^b A$AI0$y/4HYCZZ[A 45 A AFYY&r&r*)rrktypingrrimage_processing_utilsr image_utilsrprocessing_utilsrr r tokenization_utils_baser r r utilsrautor get_loggerr loggerrr*__all__rr&r'rsd "2%HHOO    H %"2%"INIX # #r&