Zj,SrSSKrSSKJr SSKJrJr SSKJ r J r J r J r J r SSKJrJrJr SSKJrJr \R*"\5rS r\"S 5Vs/sH nS US S 3PM sn\"S5Vs/sH nSUSS 3PM sn-r"SS\ 5r"SS\ SS9rS\4SjrSrSr Sr!\"SS\ 55r"S/r#gs snfs snf)z Processor class for PaliGemma. N) BatchFeature) ImageInputis_valid_image)MultiModalDataProcessingKwargsProcessorMixin TextKwargsUnpack) AddedTokenPreTokenizedInput TextInput)auto_docstringloggingziz4>z3cH\rSrSr%Sr\\-\\-\\-S-\S'Sr g)PaliGemmaTextKwargs'a suffix (`str`, `list[str]`, `list[list[str]]`): The suffixes or batch of suffixes to be encoded. Only necessary for finetuning. See https://github.com/google-research/big_vision/blob/main/big_vision/configs/proj/paligemma/README.md for more information. If your prompt is " What is on the image", the suffix corresponds to the expected prediction "a cow sitting on a bench". Nsuffix) __name__ __module__ __qualname____firstlineno____doc__rr list__annotations____static_attributes__rڃ/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/paligemma/processing_paligemma.pyrr's/ ) )DO ;dCT>U UX\ \\r rc4\rSrSr%\\S'SSS.SS0S.rSrg ) PaliGemmaProcessorKwargs1 text_kwargsF)paddingreturn_mm_token_type_ids data_formatchannels_first)r% images_kwargsrN)rrrrrr _defaultsrrr r!r#r#1s)$$(- + Ir r#F)totalreturncR[U[5=(a URS5$)Nhttp) isinstancestr startswith)vals r!is_urlr4?s c3  :CNN6$::r c<[U5=(d [U5$N)r4relems r!is_image_or_image_urlr9Ds $< />$//r cF[U[5=(d [U5$r6)r0r1r9r7s r!_is_str_or_imager;Hs dS " A&;D&AAr cX2-U-UUS3$)a Builds a string from the input prompt and image tokens. For example, for the call: build_string_from_input( prompt="Prefix str" bos_token="", image_seq_len=3, image_token="", ) The output will be: "Initial str" Args: prompt (`list[Union[str, ImageInput]]`): The input prompt. bos_token (`str`): The beginning of sentence token. image_seq_len (`int`): The length of the image sequence. image_token (`str`): The image token. num_images (`int`): Number of images in the prompt.  rprompt bos_token image_seq_len image_token num_imagess r!build_string_from_inputrDLs"&)J6 7 {6(" MMr c ^\rSrSrS U4Sjjr\S S\S-S\\-\ \-\ \-S\ \ S\ 4Sjj5r SS jr\S 5rS rU=r$)PaliGemmaProcessorbNc >[US5(d [S5eURUl[US5(dK[[SSS9nSU/0nUR U5 UR [5Ul[UlO"URUlURUlUR[5 SUl SUl [TU]9XUS9 g) Nimage_seq_lengthz;Image processor is missing an `image_seq_length` attribute.rBFT) normalizedspecialadditional_special_tokens) chat_template)hasattr ValueErrorrIr IMAGE_TOKENadd_special_tokensconvert_tokens_to_idsimage_token_idrB add_tokens EXTRA_TOKENS add_bos_token add_eos_tokensuper__init__)selfimage_processor tokenizerrMkwargsrB tokens_to_add __class__s r!rYPaliGemmaProcessor.__init__ds(:;;Z[ [ / @ @y-00$[UDQK8;-HM  ( ( 7"+"A"A+"ND *D "+":":D (44D \*"' "'  =Qr imagestextr]r-c UR"[4SURR0UD6nUSR SS5nSnUc [ S5eUc[ RS5 Sn[U5(aU/nO)[U[5(a[US 5(aUGb[UGbW[S U55(Gd[ RS 5 [U[5(aQ[U[5(a<[U5[U5:wa$[ S [U5S [U5S35e[U5(aU//nO[U[[45(a&[US 5(aUVs/sHow/PM nnOZ[U[[45(a4[US [[45(a[US S 5(d [ S5e[!X!5VV s/sHTup[#UURR$UR&[([U [5(a [U 5OSS9PMV n nn O/n UHn U R+[([(UR&-5n U R-[(5nUS:waU[[(5-OS nU SUURR$-XS-n U R/U 5 M U V s/sHoS3PM n n Ub[U5(aU/nUb)UVs/sHnUURR0-PM nnUR2"U40USD6SnUSR SS5nUSR SS5nUR"W 4UUS.USD6nUR5U US/S9 0UESU0EnU(aK[6R8"US5nSU[6R8"US5S :H'UR;SU05 U(aUR=US5US'[?UUS 9$s snfs sn nfs sn fs snf)!a Returns: [`BatchFeature`]: A [`BatchFeature`] with the following fields: - **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`. If `suffix` is provided, the `input_ids` will also contain the suffix input ids. - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not `None`). - **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`. - **labels** -- Labels compatible with training if `suffix` is not None tokenizer_init_kwargsr%rNTzF`images` are expected as arguments to a `PaliGemmaProcessor` instance.z]You are using PaliGemma without a text prefix. It will perform as a picture-captioning model.rc34# UHn[U;v M g7fr6)rP).0samples r! .PaliGemmaProcessor.__call__..s@4{f,4saLYou are passing both `text` and `images` to `PaliGemmaProcessor`. The processor expects special image tokens in the text, as many tokens as there are images per each text. It is recommended to add `` tokens in the very beginning of your text. For this call, we will infer how many images each text has and add special tokens.z Received z images for zK prompts. Each prompt should be associated with an image or list of images.zAimages must be an image, list of images or list of list of imagesr>r=r* pixel_valuesreturn_tensorsr') text_pairreturn_token_type_idsimage) modalities input_idsitoken_type_idslabelsmm_token_type_ids)data tensor_type) _merge_kwargsr#r\ init_kwargspoprOlogger warning_oncer;r0ranywarninglenrtupleziprDr@rIrPreplacerfindappend eos_tokenr[_check_special_mm_tokensnparrayupdatecreate_mm_token_type_idsr)rZrarbr] output_kwargsrrprqr? image_list input_stringsexpanded_samplesrhexpanded_samplebos_rfind_index bos_indexsfxrmrnr'inputs return_datarus r!__call__PaliGemmaProcessor.__call__sU(** $ "&.."<"<  }-11(DA $ >ef f <   o D D ! !6D d # #(8a(A(A    2@4@@@<dD))j.F.F6{c$i/('F }LT LWX "&))%hZFu 66>&QR);T;T39:6%g6F:Fve}55"6!9tUm<<&vay|44$%hii/2$.? !/@*,%"&..":":&*&;&;$/6@T6R6R3z?XY /@ ! $& "F&,nn[+PTPePeBe&fO&5&;&;K&HOFUY[F[#k2B BabI' 3dnn6N6NNQ`akQll$%++O<#>N N=M682=M N  "26":":XF  @FGcDNN444FG++FUmO6TUVde &}599:JDQ#0#?#C#CD^`d#e   "7 M*   %%mV %R>>>  !XXf[12F>BF288F#345: ;   &1 2 #/3/L/L[YdMe/fK+ ,.IIq; !(!O Hs P;AQ9Q&#Q c 0nUb;UR/[U5-nS/[U5-nURXES.5 [S0UD6$)ax Computes the number of placeholder tokens needed for multimodal inputs with the given sizes. Args: image_sizes (list[list[str]], *optional*): The input sizes formatted as (height, width) per each image. Returns: `MultiModalData`: A `MultiModalData` object holding number of tokens per each of the provided input modalities, along with other useful data. rk)num_image_tokensnum_image_patchesr)rIrrr)rZ image_sizesr] vision_datarrs r!_get_num_multimodal_tokens-PaliGemmaProcessor._get_num_multimodal_tokenssZ  " $ 5 56[9II !"c+&6 6    4Dm n, ,,r c~URRSS/-nURRn[X-5$)Nrtru)r\model_input_namesr[r)rZtokenizer_input_namesimage_processor_input_namess r!r$PaliGemmaProcessor.model_input_names s? $ @ @DTV^C_ _&*&:&:&L&L#)GHHr )rIrBrS)NNN)NNr6)rrrrrYrrrr rr r#rrrpropertyrr __classcell__)r_s@r!rFrFbs R8%)Z^tJT!tJ++d9o=EV@WWtJ12 tJ  tJtJl-$IIr rF)$rnumpyrfeature_extraction_utilsr image_utilsrrprocessing_utilsrrr r r tokenization_utils_baser r rutilsrr get_loggerrr|rPrangerUrr#boolr4r9r;rDrF__all__)is0r!rs45PO,   H % ).t5A$qgQ5RWX[R\8]R\Q4#waR\8]] ]*] /u ;4; 0BN,jIjIjIZ Y68]s B?0C