fThO3SrSSKJr SSKJrJrJrJr SSKJ r SSK J r J r J r SSKJrJrJrJrJr SSKJrJr SS KJr \(aSS KJr \R4"\5rS \4S jrS r"SS\SS9r "SS\SS9r!"SS\5r"S/r#g)z Processor class for IDEFICS2. ) accumulate) TYPE_CHECKINGListOptionalUnion) BatchFeature) ImageInputis_valid_image load_image) ImagesKwargsProcessingKwargsProcessorMixinUnpack!_validate_images_text_input_order) AddedToken TextInput)logging)PreTokenizedInputreturncR[U[5=(a URS5$)Nhttp) isinstancestr startswith)vals h/var/www/auris/envauris/lib/python3.13/site-packages/transformers/models/idefics2/processing_idefics2.pyis_urlr*s c3  :CNN6$::c<[U5=(d [U5$N)rr )elems ris_image_or_image_urlr#.s $< />$//rc&\rSrSr%\\\S'Srg)Idefics2ImagesKwargs2 image_seq_lenN)__name__ __module__ __qualname____firstlineno__rint__annotations____static_attributes__r(rrr%r%2s C= rr%F)totalc2\rSrSr%\\S'SSSS.0S.rSrg) Idefics2ProcessorKwargs6 images_kwargsTF)add_special_tokenspaddingis_split_into_words) text_kwargsr4r(N)r)r*r+r,r%r. _defaultsr/r(rrr2r26s$''#'#(  Irr2c ^\rSrSrSrSS/rSS/rSrSrSS\ S\ \ 4U4S jjjr S r SS \\\\\\\4S \\S \\\S 4S\\S\4SjjrSrSr\S5rSrU=r$)Idefics2ProcessorCa Constructs a IDEFICS2 processor which wraps a LLama tokenizer and IDEFICS2 image processor into a single processor. [`IdeficsProcessor`] offers all the functionalities of [`Idefics2ImageProcessor`] and [`LlamaTokenizerFast`]. See the docstring of [`~IdeficsProcessor.__call__`] and [`~IdeficsProcessor.decode`] for more information. Args: image_processor (`Idefics2ImageProcessor`): An instance of [`Idefics2ImageProcessor`]. The image processor is a required input. tokenizer (`PreTrainedTokenizerBase`, *optional*): An instance of [`PreTrainedTokenizerBase`]. This should correspond with the model's text model. The tokenizer is a required input. image_seq_len (`int`, *optional*, defaults to 64): The length of the image sequence i.e. the number of tokens per image in the input. This parameter is used to build the string from the input prompt and image tokens and should match the config.perceiver_config.resampler_n_latents value for the model used. chat_template (`str`, *optional*): A Jinja template which will be used to convert lists of messages in a chat into a tokenizable string. image_processor tokenizerr' chat_templateIdefics2ImageProcessor AutoTokenizerc J>Uc [S5eUc [S5e[US5(d[SSSS9RUl[SSSS9RUlS URUR /0nUR U5 URUR 5UlO3URUlUR UlURUl[S SSS9Ul UR S UR/05 X0l [TU]5XUS 9 g) Nz)You need to specify an `image_processor`.z"You need to specify a `tokenizer`. image_tokenzFT) normalizedspecialzadditional_special_tokensz)r?) ValueErrorhasattrrcontentfake_image_tokenrCr5convert_tokens_to_idsimage_token_idimage_boundary_tokenend_of_utterance_tokenr'super__init__)selfr=r>r'r?kwargs tokens_to_add __class__s rrPIdefics2Processor.__init__\s  "HI I  AB By-00$./JW\fj$k$s$sD !))tT\\D 84;P;PRVRbRb:cdM  ( ( 7"+"A"A$BRBR"SD $-$B$BD !(44D "+":":D &01ERWae&f#$$&ADD_D_C`%ab* =Qrc/nUHnn/nUHRn[U5(aURU5 M&[U5(dM8UR[U55 MT URU5 Mp U$r!)r appendrr )rQprompts prompt_imagespromptimagesr"s r_extract_images_from_prompts.Idefics2Processor._extract_images_from_promptsusi FF!$''MM$'D\\MM*T"23    (rr[textrrRrc @UcUc [S5e[X5upUR"[4SURR 0UD6nUSR SS5nUbUO URnUSR SS5n/n 0n UGb5[U[5(aU/nO8[U[5(d#[US[5(d [S 5eURn URn U X-U 3n URR(a U S -n US -n/nUH\nU RUR!U 55 UR#X5nUR#U U 3U 5nURU5 M^ UR"U40USD6nUR%UUS /S 9 U R'U5 UGb[)U5(aU//nGO[U[[*45(a[)US5(aUb[-U 5[/U5:wa*[S W S[-U 5SU S[/U5S3 5eS/[[1U 55-n[3[/U 55Vs/sHnUUUUUS-PM nnO^U/nOZ[U[[*45(d?[US[[*45(d![)USS5(d [S5eUVs/sHn[/U5PM nnUbUU :Xd[SU SUS35eUVVs/sHoVs/sHn[5U5PM snPM nnnUR"U40USD6nU R'U5 [7XS9$s snfs snfs snfs snnf)a Processes the input prompts and returns a BatchEncoding. Example: ```python >>> import requests >>> from transformers import Idefics2Processor >>> from transformers.image_utils import load_image >>> processor = Idefics2Processor.from_pretrained("HuggingFaceM4/idefics2-8b", image_seq_len=2) >>> processor.image_processor.do_image_splitting = False # Force as False to simplify the example >>> url1 = "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" >>> url2 = "https://cdn.britannica.com/59/94459-050-DBA42467/Skyline-Chicago.jpg" >>> image1, image2 = load_image(url1), load_image(url2) >>> images = [[image1], [image2]] >>> text = [ ... "In this image, we see", ... "bla bla bla", ... ] >>> outputs = processor(images=images, text=text, return_tensors="pt", padding=True) >>> input_ids = outputs.input_ids >>> input_tokens = processor.tokenizer.batch_decode(input_ids) >>> print(input_tokens) [' In this image, we see', ' bla bla bla'] ``` Args: images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`, *optional*): The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch tensor. If is of type `List[ImageInput]`, it's assumed that this is for a single prompt i.e. of batch size 1. text (`Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]]`, *optional*): 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). Wherever an image token, `` is encountered it is expanded to `` + `` * `image_seq_len` * `. return_tensors (`Union[str, TensorType]`, *optional*): If set, will return tensors of a particular framework. See [`PreTrainedTokenizerFast.__call__`] for more information. Nz+You must provide either `text` or `images`.tokenizer_init_kwargsr4r'r8return_tensorsrzAInvalid input text. Please provide a string, or a list of stringsimage) modalitieszThe total number of zP tokens in the prompts should be the same as the number of images passed. Found  z tokens and z images.zdInvalid input images. Please provide a single image or a list of images or a list of list of images.z!The number of images in the text z and images z should be the same.) tensor_type)rGr _merge_kwargsr2r> init_kwargspopr'rrlistrJrCr=do_image_splittingrWcountreplace_check_special_mm_tokensupdater#tuplesumlenrranger r )rQr[r^audiovideosrR output_kwargsr'ran_images_in_textinputsrJrC image_strprompt_stringssample text_inputscumsum_images_in_textin_images_in_imagesim image_inputss r__call__Idefics2Processor.__call__sl N(N 78H7IWiVjj~ GMMfF7"z"~7fFM//Y-:XYL MM, 'F??7 "D8Ms$?N <N3 N<N NNc:URR"U0UD6$)z This method forwards all its arguments to LlamaTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring of this method for more information. )r> batch_decoderQargsrRs rrIdefics2Processor.batch_decode s ~~**D;F;;rc:URR"U0UD6$)z This method forwards all its arguments to LlamaTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )r>decoders rrIdefics2Processor.decodes ~~$$d5f55rcURRnURRn[[R X-55$r!)r>model_input_namesr=rkdictfromkeys)rQtokenizer_input_namesimage_processor_input_namess rr#Idefics2Processor.model_input_namess< $ @ @&*&:&:&L&L#DMM"7"UVWWr)rNrJr'rCrL)N@N)NNNN)r)r*r+r,__doc__ attributes valid_kwargsimage_processor_classtokenizer_classr-rrrPr\rr rrrr2r rrrpropertyrr/ __classcell__)rTs@rr;r;Cs&$[1J#_5L4%OhlR>ARW_`cWdRR2 OSbf J@j$z"2Dj9I4JJKJ@I2DOTJ]E^^_J@ 01 J@ J@X<6XXrr;N)$r itertoolsrtypingrrrrfeature_extraction_utilsr image_utilsr r r processing_utilsr rrrrtokenization_utils_baserrutilsrr get_loggerr)loggerboolrr#r%r2r;__all__r(rrrs!774AA=<   H %;4;0!