T^(h+dZddlmZmZddlmZddlmZmZm Z ddl m Z m Z m Z mZddlmZmZddlmZej(eZGd d e d Zd efdZdZGdde ZdgZy)z Processor class for Pixtral. )ListUnion) BatchFeature) ImageInputis_valid_image load_image)ProcessingKwargsProcessorMixinUnpack!_validate_images_text_input_order)PreTokenizedInput TextInput)loggingc eZdZddiiddidZy)PixtralProcessorKwargspaddingFreturn_tensorspt) text_kwargs images_kwargs common_kwargsN)__name__ __module__ __qualname__ _defaultsl/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/pixtral/processing_pixtral.pyrrs$ u  d IrrF)totalreturncHt|txr|jdS)Nhttp) isinstancestr startswith)vals ris_urlr(,s c3  :CNN6$::rc2t|xs t|SN)r(r)elems ris_image_or_image_urlr,1s $< />$//rc eZdZdZddgZgdZdZdZ ddedeffd Z dd e d e e e ee ee fd eed efdZdZdZedZxZS)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 tokenizer) chat_template patch_sizespatial_merge_size image_tokenimage_break_tokenimage_end_tokenAutoImageProcessor AutoTokenizerr2r3c  p||_||_||_||_||_t ||||y)N)r1)r2r3r4r5r6super__init__) selfr/r0r2r3r1r4r5r6kwargs __class__s rr;zPixtralProcessor.__init__[s@%"4&!2. )=Qrimagestextr=r!c t||\}}|jtfd|jji|}|j |j z}|t|r|g}nt|ttfrt|drndt|ttfrCt|dttfr*t|ddr|D cgc] }|D]} |  }}} n td|D cgc]} t| tr t| n| !}} |j|fd|i|d} ni} t|tr|g}n.t|tst|dts td|} | jdt!| d} g} g}|D]}|j"|vrt%| \}}||z}||z}|j"g|z|j&gzg|z}|Dcgc] }|D]}| }}}|j(|d <d j+|}|j-||j/|j"d d }|j"|vrd |vr)|j1d}|j/d |d }d |vr)| j-||j| fi|d }t3i|| |ddScc} }wcc} wcc}}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_kwargsrzdInvalid input images. Please provide a single image, a list of images, or a list of lists of images.r2rzAInvalid input text. Please provide a string, or a list of strings pixel_values image_sizesz rrr)data tensor_type)r _merge_kwargsrr0 init_kwargsr2r3r,r$listtuple ValueErrorr%r r/getiterr4nextr5r6joinappendreplacepopr)r<r?r@audiovideosr= output_kwargsr2sublistimageim image_inputsprompt_stringsrDreplace_stringssampleheightwidthnum_height_tokensnum_width_tokensreplace_tokensitem replace_str text_inputss r__call__zPixtralProcessor.__call__ns'R9F *** " "&.."<"<  __t'>'>>  $V, FT5M27LVTUY7W6D%=1vay4-8)&)A,7/5KG7K%%K%KK zOUU 2s(;jnCUFU/4//p:pQ^_nQopLL dC 6DD$' 47C0H`a a   N + 7|M:;KN O .&&&0$($5MFE(.*(<%', ':$))*-==AWAW@XX&)&*N;I%]wU\%]Td%]d%]N%])-)=)=N2&"$''."9K#**;7#^^D,<,\]m>n  YL V6&^sK 4$K/Kc:|jj|i|S)z This method forwards all its arguments to LlamaTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring of this method for more information. )r0 batch_decoder<argsr=s rrjzPixtralProcessor.batch_decodes +t~~**D;F;;rc:|jj|i|S)z This method forwards all its arguments to LlamaTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )r0decoderks rrnzPixtralProcessor.decodes %t~~$$d5f55rc|jj}|jj}ttj ||zSr*)r0model_input_namesr/rLdictfromkeys)r<tokenizer_input_namesimage_processor_input_namess rrpz"PixtralProcessor.model_input_namessA!% @ @&*&:&:&L&L#DMM"7:U"UVWWr)NNrGNz[IMG]z [IMG_BREAK]z [IMG_END])NNNN)rrr__doc__ attributes valid_kwargsimage_processor_classtokenizer_classintr;rrrrrr rrrhrjrnpropertyrp __classcell__)r>s@rr.r.5s2$[1JL1%O"#'#R R  R*"^b k k I0$y/4HYCZZ[k /0 k  k \<6XXrr.N)rvtypingrrfeature_extraction_utilsr image_utilsrrr processing_utilsr r r r tokenization_utils_baserrutilsr get_loggerrloggerrboolr(r,r.__all__rrrrss4AAkkC   H % -U ;4; 0{X~{X|  r