Zj;.SrSSKrSSKJr SSKJrJr SSKrSSK J r SSK J r J r Jr SSKJrJrJrJr SS KJrJrJr SS KJrJr \(aSS KJr \R8"\5rS \4S jr Sr!Sr"Sr#Sr$"SS\SS9r%\"SS\55r&S/r'g)z Processor class for Idefics3. N) accumulate) TYPE_CHECKINGUnion) BatchFeature) ImageInputis_valid_image load_image)MultiModalDataProcessingKwargsProcessorMixinUnpack) AddedToken BatchEncoding TextInput)auto_docstringlogging)PreTokenizedInputreturncR[U[5=(a URS5$)Nhttp) isinstancestr startswith)vals ځ/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/idefics3/processing_idefics3.pyis_urlr%s c3  :CNN6$::c<[U5=(d [U5$N)rr )elems ris_image_or_image_urlr")s $< />$//rc Sn[U5H7n[U5H nUUSUS-SUS-S3-UU--- nM" US- nM9 USU3U-UU--U-- nU$)zKPrompt with expanded image tokens for when the image is split into patches. )range) image_seq_len image_rows image_colsfake_token_around_image image_tokenglobal_img_tokentext_split_imagesn_hn_ws r_prompt_split_imager4-sZ $C *+sQwiuS1WIQ/OOU`TaerRrr  % T! ! $ %&   M] * +% % ' rc&UU-UU--U-$)z5Prompt with expanded image tokens for a single image.)r+r.r/r0s r_prompt_single_imager7@s6 # #   M] * +% % 'rcLUS:XaUS:Xa [UUUUS9$[X XXE5$)Nr)r.r/r0)r7r4)r,r-r+r.r/r0s rget_image_prompt_stringr9Js@Q:?# $;#-   :  rc,\rSrSrSSSSS.SS0S.rSrg) Idefics3ProcessorKwargsYTF)add_special_tokenspaddingis_split_into_wordsreturn_mm_token_type_idsreturn_row_col_info) text_kwargs images_kwargsr6N)__name__ __module__ __qualname____firstlineno__ _defaults__static_attributes__r6rrr;r;Ys(#'#((-   "4  Irr;F)totalc ^\rSrSrSS\S\S-4U4SjjjrSr\SS\ \ \ -\ \ \ -S\ \ S \ \ \ S 4S\S-S \ \S \4 S jj5rS \ S\ \S \ \ \4SjrSSjrSrU=r$)Idefics3ProcessorgNr+ chat_templatec 2>[SSSS9RUl[SSSS9RUl[SSSS9RUlSUlX0lURUR5UlURUR5Ul URUR 5Ul [S5VVs/sH3n[S5H orRS US -S US -S 35PM" M5 snnUl [R"S 5UlSURURUR/0nUR!U5 URUR5Ul["T U]H"X4SU0UD6 gs snnf)aw image_seq_len (`int`, *optional*, defaults to 169): 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 value the model used. It is computed as: image_seq_len = int(((image_size // patch_size) ** 2) / (scale_factor**2)) zFT) normalizedspecialzzz r%r&r'r(z*(\n?\n?|\n?)+additional_special_tokensrNN)rcontentfake_image_tokenr/end_of_utterance_tokenglobal_image_tagr+convert_tokens_to_idsimage_token_idfake_image_token_idglobal_image_token_idr* row_col_idsrecompile%_regex_to_remove_extra_special_tokensr=super__init__) selfimage_processor tokenizerr+rNkwargsij tokens_to_add __class__s rraIdefics3Processor.__init__is!++FSXbf g o o%iE4PXX&01ERWae&f&n&n# .*'==d>N>NO#,#B#B4CXCX#Y %.%D%DTEZEZ%["SXYZS[ S[aejklem`a + +eAE7%Awa,H Iem IS[  68ZZ@m5n2 (%%  ++*  $$]3'==d>N>NO [=[TZ[% s :Fc/nUHnn/nUHRn[U5(aURU5 M&[U5(dM8UR[U55 MT URU5 Mp U$r )r appendrr )rbprompts prompt_imagespromptimagesr!s r_extract_images_from_prompts.Idefics3Processor._extract_images_from_promptssi FF!$''MM$'D\\MM*T"23    (rrptextrrerc v UcUc [S5eUR"[4SURR0UD6nUbUO UR nUSR SS5nUSR SS5n/n/n 0n Ub{[U[5(aU/nO8[U[5(d#[US[5(d [S 5eUV s/sHoRUR5PM nn UGb[U5(aU//nGO,[U[[45(a[US5(aUb[U5[U5:wa>[S URS [U5S URS [U5S3 5eS/[[!U55-n [#[U55V s/sHn XU XS-PM nn O^U/nOZ[U[[45(d?[US[[45(d![USS5(d [S5eUV s/sHn [U 5PM n n UV Vs/sH0oVs/sH n[%U5(a ['U5OUPM" snPM2 nn nUR("U40USD6nU R+U5 UGbX:wa[SUSU S35eU R SUVs/sH nS/U-PM sn5nU R SUVs/sH nS/U-PM sn5nUR,nURnUR.n/n/n[1UUU5Hun nn/n/nU5H^unn[3UUUUUUS9nUR S-U-S-nUR5UR S-UU--5 UR5U5 M` UR5U5 U R7U5n [U 5S:Xa [S5eU Sn [9U5Hun nU UU U S--- n M UR5U 5 M UR"U40USD6n!UR;UU!S/S9 U R+U!5 O`Ub][=U5(a%[S[U5S URS35eUR"S#SU0USD6n!U R+U!5 U(aUR?U S W5U S!'[AXS"9$s sn fs sn fs sn fs snfs snn fs snfs snf)$z image_seq_len (`int`, *optional*): The length of the image sequence. If not provided, the default value of self.image_seq_len is used. image_seq_len should be equal to int(((image_size // patch_size) ** 2) / (scale_factor**2)) Nz+You must provide either `text` or `images`.tokenizer_init_kwargsrBr@Freturn_tensorsrzAInvalid input text. Please provide a string, or a list of stringszThe total number of zP tokens in the prompts should be the same as the number of images passed. Found  z tokens and z images.r&zdInvalid input images. Please provide a single image or a list of images or a list of list of images.rCz!The number of images in the text z and images z should be the same.rowscols)r/r.r0rz.The image token should be present in the text.image) modalitieszFound z. tokens in the text but no images were passed.rs input_idsmm_token_type_ids)data tensor_typer6)! ValueError _merge_kwargsr;rd init_kwargsr+poprrlistcountr/r"tuplesumlenrr*rr rcupdaterUrWzipr9rlsplit enumerate_check_special_mm_tokensanycreate_mm_token_type_idsr)"rbrprsr+re output_kwargsr@rvn_images_in_textn_images_in_imagesinputssamplecumsum_images_in_textrfim image_inputsn_imagesr,r-rUr/r0prompt_stringsbatch_image_seq_lengths sample_rows sample_colsimage_prompt_stringsimage_seq_lengthsn_rowsn_colsimage_prompt_string row_length split_sample text_inputss" r__call__Idefics3Processor.__call__s T R  $V,,!(FT5M227LVTUY7W7W#+,F ;(243C3C2DE&&)*:&;%N>N=O|\_`f\g[hhpr ./C$zBR7S2T,T)"'s+;'A#\X[^bXb#\#\J JNbf$( @ET*--T*5E0FF@EI2DOTJ]E^^_@ETz @E 01 @E  @E@ED!$!QUVYQZ!_cdhildm_n!*#-#-rrL)(__doc__r] itertoolsrtypingrrnumpyrfeature_extraction_utilsr image_utilsrr r processing_utilsr r r rtokenization_utils_baserrrutilsrrr get_loggerrDloggerboolrr"r4r7r9r;rL__all__r6rrrs '4AAXXKK,<   H %;4;0&  .e m-m-m-`  r