hd.dZddlmZddlZddlmZddlmZm Z ddl m Z m Z m Z mZddlmZmZdd lmZmZerd d lmZej.eZGd d e dZdefdZdZGdde ZdgZy)z Processor class for Pixtral. )UnionN) BatchFeature) ImageInputis_valid_image)MultiModalDataProcessingKwargsProcessorMixinUnpack)PreTokenizedInput TextInput)is_vision_availablelogging)get_resize_output_image_sizec"eZdZdddiddidZy)PixtralProcessorKwargsF)paddingreturn_mm_token_type_idsreturn_tensorspt) text_kwargs images_kwargs common_kwargsN)__name__ __module__ __qualname__ _defaultsl/var/www/html/eduruby.in/venv/lib/python3.12/site-packages/transformers/models/pixtral/processing_pixtral.pyrr*s%(-  d Ir rF)totalreturncHt|txr|jdS)Nhttp) isinstancestr startswith)vals r!is_urlr*8s c3  :CNN6$::r c2t|xs t|SN)r*r)elems r!is_image_or_image_urlr.=s $< />$//r c eZdZdZddgZdZdZ ddedeffd Z dd e d e e e e e e e fd eed efd ZddZedZxZS)PixtralProcessorab Constructs a Pixtral processor which wraps a Pixtral image processor and a Pixtral tokenizer into a single processor. [`PixtralProcessor`] offers all the functionalities of [`CLIPImageProcessor`] and [`LlamaTokenizerFast`]. See the [`~PixtralProcessor.__call__`] and [`~PixtralProcessor.decode`] for more information. Args: image_processor ([`PixtralImageProcessor`], *optional*): The image processor is a required input. tokenizer ([`LlamaTokenizerFast`], *optional*): The tokenizer is a required input. patch_size (`int`, *optional*, defaults to 16): Patch size from the vision tower. spatial_merge_size (`int`, *optional*, defaults to 1): The downsampling factor for the spatial merge operation. chat_template (`str`, *optional*): A Jinja template which will be used to convert lists of messages in a chat into a tokenizable string. image_token (`str`, *optional*, defaults to `"[IMG]"`): Special token used to denote image location. image_break_token (`str`, *optional*, defaults to `"[IMG_BREAK]"`): Special token used to denote the end of a line of pixels in an image. image_end_token (`str`, *optional*, defaults to `"[IMG_END]"`): Special token used to denote the end of an image input. image_processor tokenizerAutoImageProcessor AutoTokenizer patch_sizespatial_merge_sizec  ||_||_||_|j|j|_||_||_|j|j|_|j|j |_|j|j |_|j|j|jg|_ t |-|||y)N) chat_template) r5r6 image_tokenconvert_tokens_to_idsimage_token_idimage_break_tokenimage_end_tokenimage_break_token_idimage_end_token_id image_idssuper__init__) selfr1r2r5r6r8r9r<r=kwargs __class__s r!rBzPixtralProcessor.__init___s%"4&'==d>N>NO!2.'==d>N>NO$-$C$CDDZDZ$[!"+"A"A$BVBV"W--t/H/H$JaJab )=Qr imagestextrDr#c L|jtfd|jji|}|j|j z}||j |fd|i|d}ni}t|tr|g}n.t|tst|dts td|} |jdt|d} g} g} |D]} |j| vrt| \} }| |z}||z}|jg|z|jgzg|z}|Dcgc] }|D]}| }}}|j |d <d j#|}| j%|| j'|jd d } |j| vrd | vr)| j)d}| j'd |d } d | vr)| j%| |d j)dd}|d j)dd}|j| fi|d ddi}|j+| |dg|rft-j.|d}t-j0|d}d |t-j2||j4<|j7|d<t9i|||Scc}}w)a Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text` and `kwargs` arguments to LlamaTokenizerFast's [`~LlamaTokenizerFast.__call__`] if `text` is not `None` to encode the text. To prepare the image(s), this method forwards the `images` and `kwrags` arguments to CLIPImageProcessor's [`~CLIPImageProcessor.__call__`] if `images` is not `None`. Please refer to the docstring of the above two methods for more information. 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). 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`. tokenizer_init_kwargsNr5rrzAInvalid input text. Please provide a string, or a list of strings pixel_values image_sizesz rrrrFimage) modalities input_idsmm_token_type_ids)data tensor_type) _merge_kwargsrr2 init_kwargsr5r6r1r&r'list TypeErrorgetiterr9nextr<r=joinappendreplacepop_check_special_mm_tokensnparray zeros_likeisinr@tolistr)rCrFrGaudiovideosrD output_kwargsr5 image_inputsprompt_stringsrKreplace_stringssampleheightwidthnum_height_tokensnum_width_tokensreplace_tokenssublistitem replace_strrr text_inputs array_idsrQs r!__call__zPixtralProcessor.__call__wsR+** " "&.."<"<  __t'>'>>  /4//p:pQ^_nQopLL dC 6DD$' 47C0H_` `   N + 7|M:;KN O .&&&0$($5MFE(.*(<%', ':$))*-==AWAW@XX&)&*N;I%]wU\%]Td%]d%]N%])-)=)=N2&"$''."9K#**;7#^^D,<,  '')9A)=AR(RS T"#c+&6 6    4D[lm n, ,,r cl|jj}|jj}||zdgzS)NrK)r2model_input_namesr1)rCtokenizer_input_namesimage_processor_input_namess r!rz"PixtralProcessor.model_input_namess7 $ @ @&*&:&:&L&L#$'BBm_TTr )NNrNz[IMG]z [IMG_BREAK]z [IMG_END])NNNNr,)rrr__doc__ attributesimage_processor_classtokenizer_classintrBrrr r rVr rrrvrpropertyr __classcell__)rEs@r!r0r0As2$[1J0%O"#'#R R  R4"^b b^b^I0$y/4HYCZZ[b^ /0 b^ b^H"-HUUr r0) rtypingrnumpyr`feature_extraction_utilsr image_utilsrrprocessing_utilsrr r r tokenization_utils_baser r utilsrrimage_processing_pixtralr get_loggerrloggerrboolr*r.r0__all__rr r!rs45 D1F   H % -U ;4; 0BU~BUJ  r