ZjL5SSKrSSKJr SSKJr SSKJrJrJ r J r SSK J r J r SSKJrJr SSKJr \R&"\5r"S S \S S 9r\"S S\ 55rS/rg)N) BatchFeature) ImageInput)MultiModalDataProcessingKwargsProcessorMixinUnpack)PreTokenizedInput TextInput)auto_docstringlogging) VideoInputc*\rSrSrSSSS.SS0S.rSrg) Glm4vProcessorKwargs"FT)paddingreturn_token_type_idsreturn_mm_token_type_idsreturn_metadata) text_kwargs videos_kwargsN)__name__ __module__ __qualname____firstlineno__ _defaults__static_attributes__r{/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/glm4v/processing_glm4v.pyrr"s#%*(, ,T2 IrrF)totalc ^\rSrSrSU4Sjjr\SS\S-S\\-\ \-\ \-S\ S-S\ \ S\ 4 S jj5rSS jrSS jr\U4S j5rS \ S\ \ \4SjrSrSrU=r$)Glm4vProcessor-Nc >[US5(dSO URUl[US5(dSO URUl[USS5(a UROUR UR5Ul[USS5(a UR OUR UR5Ul[TU]!XX4S9 UR S5Ul UR S 5Ul g) N image_tokenz <|image|> video_tokenz <|video|>image_token_idvideo_token_id) chat_templatez<|begin_of_video|>z<|end_of_video|>) hasattrr&r'getattrr(convert_tokens_to_idsr)super__init__video_start_id video_end_id)selfimage_processor tokenizervideo_processorr*kwargs __class__s r r/Glm4vProcessor.__init__/s.5i.O.O;U^UjUj.5i.O.O;U^UjUjy"2D99  $ $001A1AB y"2D99  $ $001A1AB  _b'==>RS%;;aSmolVLM requires frame timestamps to construct prompts, but the `fps` of the input video could not be inferred. Probably `video_metadata` was missing from inputs and you passed pre-sampled frames. Defaulting to `fps=24`. Please provide `video_metadata` for more accurate results.rreturn_tensorsrFimagevideo) modalities input_idsmm_token_type_ids)data tensor_typer) _merge_kwargsrr4 init_kwargsr3r5getpop isinstancelistcopy merge_sizerangelenr&prodreplacer'fpslogger warning_once timestampsappendreplace_frame_token_id_check_special_mm_tokenscreate_mm_token_type_idsr)r2r9r:r;r6 output_kwargs image_inputsr@ videos_inputsrArB merge_lengthindexinum_image_tokens video_index num_framesvideo_structuremetadatar_unique_timestampsidxselected_timestamps frame_idx timestamp_secframe_structurerHr text_inputss r __call__Glm4vProcessor.__call__@sj***  "&.."<"<   //`v`A_`L)*:;NL!N   00aa-P_B`aM::/00!.!2!23C!D!./?!@*+;.>@QTd@dfghDGQJE&&$'1'//*;T=M=MN &  %//::A=LK3t9%&&$'1!/!.>QRSDG&388:lJnNijkNll%&+:%6 ++tw6&*good6F6FHY\lHlno&pDG&7 1$KG&&$'1J'//*;T=M=MNM&N'}599:JDQ#0#?#C#CD^`e#f nnTJ]=-IJ  %%dKWgDV%W #/3/L/L[YdMe/fK+ ,!QK!Q>PRSM   (&**<>a$BVBVBaBaJ#.!"-J$$@@\*\m\"- !SddRc; A !=Rc d   4Dm n  "0::>>PRSM   (#.!"-J$$@@\*\m\"- !SddRc; A !=Rc d.>* +, ,,#! e ! es*(EE 6(E$Ec BURR"U4UUS.UD6$)a* Post-process the output of the model to decode the text. Args: generated_outputs (`torch.Tensor` or `np.ndarray`): The output of the model `generate` function. The output is expected to be a tensor of shape `(batch_size, sequence_length)` or `(sequence_length,)`. skip_special_tokens (`bool`, *optional*, defaults to `True`): Whether or not to remove special tokens in the output. Argument passed to the tokenizer's `batch_decode` method. clean_up_tokenization_spaces (`bool`, *optional*, defaults to `False`): Whether or not to clean up the tokenization spaces. Argument passed to the tokenizer's `batch_decode` method. **kwargs: Additional arguments to be passed to the tokenizer's `batch_decode method`. Returns: `list[str]`: The decoded text. )skip_special_tokensclean_up_tokenization_spaces)r4 batch_decode)r2generated_outputsrrr6s r post_process_image_text_to_text.Glm4vProcessor.post_process_image_text_to_texts3(~~**  3)E    rc>>[TU]nURS5 U$)NrM)r.model_input_namesr`)r2rr7s r r Glm4vProcessor.model_input_namess#!G5  !45  rrLc/nUHn[R"U5n[R"U5n[R"X@R:HSS9n[R"X@R :HSS9nXg:nSXTUR :HU-'SXTUR :HU)-'URUR55 M U$)Nr)axisrCrD) nparray zeros_likecumsumr0r1r(r`tolist) r2rLrMinput array_idsmm_token_typesstartsendsis_video_modalitys r rc'Glm4vProcessor.create_mm_token_type_idssEI]]51N YYy,?,??aHF99Y*;*;;!DD & UVN)<)<<@QQ RXYN)<)<z<|end_of_image|>)r&int)r2rss r ra%Glm4vProcessor.replace_frame_token_id s##D$4$4#55Ec-FXEYZZr)r&r(r1r0r'r))NNNN)NNN)NN)TF)rrrrr/r rr r rUrr rrrvrrpropertyrrrcrar __classcell__)r7s@r r#r#-sP"%)Z^$( koT!ko++d9o=EV@WWkoT! ko -. ko  kokoZ$-NY^ 6!! !$!4S ?!*[[rr#)numpyrfeature_extraction_utilsr image_utilsrprocessing_utilsrrrr tokenization_utils_baser r utilsr r video_utilsr get_loggerrr]rr#__all__rrr rsl*4%XXC,%   H %+5][^][][@  r