cCi;SSKJrJr SSKrSSKJr SSKJr SSK J r J r J r J r JrJr SSKJrJr SSKJr SS KJr \R."\5r"S S \S S 9r"SS\ 5r"SS\ S S 9r"SS\ 5rS/rg))OptionalUnionN) BatchFeature) ImageInput) ImagesKwargsMultiModalDataProcessingKwargsProcessorMixinUnpack VideosKwargs)PreTokenizedInput TextInput)logging) VideoInputc0\rSrSr%\\\\4\S'Srg)Glm4vVideosProcessorKwargs$fpsN) __name__ __module__ __qualname____firstlineno__rlistfloat__annotations____static_attributes__rd/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/glm4v/processing_glm4v.pyrr$s tE{E! ""rrF)totalcF\rSrSr%\\\S'\\\S'\\\S'Srg)Glm4vImagesKwargs( patch_sizetemporal_patch_size merge_sizerN)rrrrrintrrrrr r#r#(s  !#& rr#c@\rSrSr%\\S'SSSS.SS0S.r\\S'S rg ) Glm4vProcessorKwargs. images_kwargsF)paddingreturn_token_type_idsreturn_mm_token_type_idsreturn_metadataT) text_kwargs videos_kwargsr2rN) rrrrr#r _defaultsrrrrr r*r*.s1$$%*(- ,T2 I.-rr*c ^\rSrSrSr/SQrSrSrSrSU4Sjjr SS\ \ S \ \ \\\ \\4S \ \S \\S \4 S jjrSSjrSSjrSrU=r$)Glm4vProcessor;a Constructs a GLM-4V processor which wraps a GLM-4V image processor and a GLM-4 tokenizer into a single processor. [`~Glm4vProcessor.__call__`] and [`~Glm4vProcessor.decode`] for more information. Args: image_processor ([`Glm4vProcessor`], *optional*): The image processor is a required input. tokenizer ([`PreTrainedTokenizerFast`], *optional*): The tokenizer is a required input. video_processor ([`Glm4vVideoProcessor`], *optional*): The video processor is a required input. 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 tokenizervideo_processorAutoImageProcessorAutoVideoProcessor)PreTrainedTokenizerPreTrainedTokenizerFastc >[TU]XX4S9 [US5(dSO URUl[US5(dSO URUl[ USS5(a UR OURUR5Ul[ USS5(aURUlgURUR5Ulg)N) chat_template image_tokenz <|image|> video_tokenz <|video|>image_token_idvideo_token_id) super__init__hasattrr@rAgetattrrBconvert_tokens_to_idsrC)selfr7r8r9r?kwargs __class__s r rEGlm4vProcessor.__init__Ps _b.5i.O.O;U^UjUj.5i.O.O;U^UjUjy"2D99  $ $001A1AB y"2D99  $ $ 001A1AB rimagestextvideosrJreturnc UR"[4SURR0UD6nUbUR"SSU0USD6nUSnO0nSnUb:UR "SSU0USD6nSU;aUR S 5n OUS n US n O0nSn [U[5(dU/nUR5nUbURRS -n S n [[U55Hn URX-;aRX|R5U -nX-RURS U-S5X-'U S- n URX-;aMRX-RS UR5X-'M U GbUR RS -n S n[[U55GHn UR X-;GaXS nSnW UnUR"c[$R'S5 UR"cSO UR"UlUR(SSS 2n/n[S [U55HnUR+UU5 M USUn[U5U:a.UR+U(aUSOS 5 [U5U:aM.[U5H(nUUnSURS[-U53nUU- nM* X-RUR US5X-'XR5U -XS -n[U5H;nURX-;dMX-RURS U-S5X-'M= US- nUR X-;aGMX-RS UR5X-'GM USR SS5nUSR SS5nUR"U40USD6nUR/UUSS/S9 U(aW[0R2"US5n[0R4"US5nSUUUR6:H'UR95US'[;0UEUEUEUS9$) af Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text` and `kwargs` arguments to PreTrainedTokenizerFast's [`~PreTrainedTokenizerFast.__call__`] if `text` is not `None` to encode the text. Args: images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`): The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch tensor. Both channels-first and channels-last formats are supported. text (`str`, `List[str]`, `List[List[str]]`): 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). videos (`np.ndarray`, `torch.Tensor`, `List[np.ndarray]`, `List[torch.Tensor]`): The image or batch of videos to be prepared. Each video can be a 4D NumPy array or PyTorch tensor, or a nested list of 3D frames. Both channels-first and channels-last formats are supported. return_tensors (`str` or [`~utils.TensorType`], *optional*): If set, will return tensors of a particular framework. Acceptable values are: - `'tf'`: Return TensorFlow `tf.constant` objects. - `'pt'`: Return PyTorch `torch.Tensor` objects. - `'np'`: Return NumPy `np.ndarray` objects. - `'jax'`: Return JAX `jnp.ndarray` objects. 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`. - **pixel_values_videos** -- Pixel values of videos to be fed to a model. Returned when `videos` is not `None`. - **image_grid_thw** -- List of image 3D grid in LLM. Returned when `images` is not `None`. - **video_grid_thw** -- List of video 3D grid in LLM. Returned when `videos` is not `None`. tokenizer_init_kwargsNrMr,image_grid_thwrOr2r0video_metadatavideo_grid_thwrz<|placeholder|>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.z<|begin_of_image|>z<|end_of_image|>r1return_tensorsr/Fimagevideo) modalities input_idsmm_token_type_ids)data tensor_typer) _merge_kwargsr*r8 init_kwargsr7r9pop isinstancercopyr'rangelenr@prodreplacerArlogger warning_once timestampsappendr(_check_special_mm_tokensnparray zeros_likerBtolistr)rIrMrNrOrJ output_kwargs image_inputsrS videos_inputsrTrU merge_lengthindexinum_image_tokens video_index num_framesvideo_structuremetadatarnunique_timestampsidxselected_timestamps frame_idx timestamp_secframe_structurer[r/ text_inputs array_idsr`s r __call__Glm4vProcessor.__call___sT**  "&.."<"<   //`v`A_`L)*:;NL!N   00aa-P_B`aM .!.!2!23C!D!./?!@*+;.>@QTd@dfghDGQJE&&$'1'//*;T=M=MN &  %//::A=LK3t9%&&$'1!/!t?O?O>PP`aderas`t*u'?:&7 #good.>.>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 #[!9:I " k+.F G BC i4+>+>> ?/@/G/G/IK+ ,!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)r8 batch_decode)rIgenerated_outputsrrrJs r post_process_image_text_to_text.Glm4vProcessor.post_process_image_text_to_text s3(~~**  3)E    r)r@rBrArC)NNNN)NNN)NN)TF)rrrr__doc__ attributesimage_processor_classvideo_processor_classtokenizer_classrErrrrrrrr r*rrrrr __classcell__)rKs@r r5r5;s EJ00HO  "(,^b'+ Do$DoI0$y/4HYCZZ[Do$ Do -. Do  DoL$-NY^  rr5)typingrrnumpyrqfeature_extraction_utilsr image_utilsrprocessing_utilsrr r r r r tokenization_utils_baserrutilsr video_utilsr get_loggerrrlrr#r*r5__all__rrr rsv*#4%ttC%   H %#U#  .+5 .i ^i X  r