ZjSrSSKJr SSKJr SSKJrJrJrJ r J r SSK J r J r SSKJr "SS\ S S 9r"S S \S S 9r\"S S\55rS/rg)z Processor class for Chameleon. ) BatchFeature) ImageInput)MultiModalDataProcessingKwargsProcessorMixin TextKwargsUnpack)PreTokenizedInput TextInput)auto_docstringc$\rSrSr%Sr\\S'Srg)ChameleonTextKwargsam return_for_text_completion (`bool`, *optional*, defaults to `False`): Whether the processed text is intended for text completion tasks. When `True`, the processor does not append the separator token (`sep_token`) to the end of the prompt, which is typically used for chat mode. When `False`, the separator token is appended for proper chat formatting. return_for_text_completionN)__name__ __module__ __qualname____firstlineno____doc__bool__annotations____static_attributes__rڃ/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/chameleon/processing_chameleon.pyrrs!%$rrF)totalc6\rSrSr%\\S'SSSS.SS0S.rSrg ) ChameleonProcessorKwargs* text_kwargsF)paddingrreturn_mm_token_type_idsreturn_tensorspt)r common_kwargsrN)rrrrrr _defaultsrrrrrr*s+$$*/(- d Irrc ^\rSrSrS S\S\4U4Sjjjr\SS\S-S\ \ -\ \ -\ \ -S-S\ \ S \4S jj5rSS jrS rU=r$)ChameleonProcessor8image_seq_length image_tokencX>[TU]X5 X0l[US5(a UROUUlUR UR5Ul[US5(a UROSUl[US5(a UROSUl UR UR5UlUR UR5Ul UR UR5Ul UR URUR/Ul g)z image_seq_length (`int`, *optional*, defaults to 1024): Sequence length of one image embedding. image_token (`str`, *optional*, defaults to `""`): The special token used to indicate image in the text. r+ boi_tokenz eoi_tokenzN)super__init__r*hasattrr+convert_tokens_to_idsimage_token_idr-image_start_tokenr.image_end_tokenimage_start_token_idimage_end_token_id image_ids)selfimage_processor tokenizerr*r+ __class__s rr0ChameleonProcessor.__init__:s 4 04;I}4U4U900[f'==d>N>NO#*9k#B#BI   7>i6U6Uy22[c'==d>N>NO$-$C$CDDZDZ$[!"+"A"A$BVBV"W--t/H/H$JaJabrNimagestextkwargsreturnc [U[5(aU/nO8[U[5(d#[US[5(d [S5eUcUc [ S5eUR "[ 4SURR0UD6nUSRSS5n/nURURUR--UR-nUHOnURURU5nU(dXRR- nUR!U5 MQ 0n UbUR""U40US D6n USRS S5n USRS S5n UR"U40USDS S0D6n UR%XlS /S 9 U (aUR'U S5U S'[)0U EU EU S9$)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`. - **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`. zAInvalid input text. Please provide a string, or a list of stringsNz&You must provide either text or imagestokenizer_init_kwargsr rF images_kwargsr#r"image) modalities input_idsmm_token_type_ids)data tensor_type) isinstancestrlist TypeError ValueError _merge_kwargsrr; init_kwargspopr4r+r*r5replace sep_tokenappendr:_check_special_mm_tokenscreate_mm_token_type_idsr) r9r>r?r@ output_kwargsrprompt_stringsone_img_tokenssample image_inputsr#r" text_inputss r__call__ChameleonProcessor.__call__Os$ dC 6DD$'' 47C0H0H_` ` URS-/[U5-nS/[U5-nURXES.5 [S0UD6$)a{ Computes the number of placeholder tokens needed for multimodal inputs with the given sizes. Args: image_sizes (`list[list[int]]`, *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. )num_image_tokensnum_image_patchesr)r*lenupdater)r9 image_sizesr@ vision_datardres r_get_num_multimodal_tokens-ChameleonProcessor._get_num_multimodal_tokenss_  " $ 5 5 9:S=MM !"c+&6 6    4Dm n, ,,r)r5r7r8r*r4r6r+r3)iz)NN)N)rrrrintrMr0r rr r rNr rrr_rjr __classcell__)r<s@rr(r(8scSc^acc*%)ae3^T!3^++d9o=EV@WWZ^^3^12 3^  3^3^j--rr(N)rfeature_extraction_utilsr image_utilsrprocessing_utilsrrrrr tokenization_utils_baser r utilsr rrr(__all__rrrrtsk5%D#%*E% /u a-a-a-H r