S^(hddlmZmZmZmZddlmZddlmZddl m Z m Z m Z ddl mZmZddlmZdd lmZGd d e d ZGdde ZdgZy))DictListOptionalUnion) BatchFeature) ImageInput)ProcessingKwargsProcessorMixinUnpack)PreTokenizedInput TextInput) TensorType) AutoTokenizerc6eZdZddidddejdZy)AriaProcessorKwargspaddingF)max_image_size split_image) text_kwargs images_kwargsreturn_tensorsN)__name__ __module__ __qualname__rPYTORCH _defaultsf/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/aria/processing_aria.pyrrs- u "  %,, Ir!rF)totalc eZdZdZddgZddgZdZdZ ddee e fde e de e ee efefffd Z dd eeeeeeefd e ed eed efd ZdZdZedZxZS) AriaProcessora AriaProcessor is a processor for the Aria model which wraps the Aria image preprocessor and the LLama slow tokenizer. Args: image_processor (`AriaImageProcessor`, *optional*): The AriaImageProcessor to use for image preprocessing. tokenizer (`PreTrainedTokenizerBase`, *optional*): An instance of [`PreTrainedTokenizerBase`]. This should correspond with the model's text model. The tokenizer 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. size_conversion (`Dict`, *optional*): A dictionary indicating size conversions for images. image_processor tokenizer chat_templatesize_conversionAriaImageProcessorrc|ddd}|jDcic]\}}t||c}}|_||j|j|_t ||||ycc}}w)N)ir)r()itemsintr) pad_token unk_tokensuper__init__)selfr&r'r(r)kv __class__s r"r3zAriaProcessor.__init__@sv  "$'c2O6E6K6K6MNdaA N  Y%8%8%@"+"5"5I  )=Q OsA-textimageskwargsreturnc |jtfd|jji|}t |t r|g}n.t |t st |dt s td||j|fi|d}|j|jjd}g} |jd|z} |D]P} | j|jj|jj| z} | j| Rni}|} |j| fi|d} t!i| |S) a Main method to prepare for the model one or several sequences(s) and image(s). Args: text (`TextInput`, `PreTokenizedInput`, `List[TextInput]`, `List[PreTokenizedInput]`): The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set `is_split_into_words=True` (to lift the ambiguity with a batch of sequences). images (`ImageInput`): The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch tensor. Both channels-first and channels-last formats are supported. Returns: [`BatchFeature`]: A [`BatchFeature`] with the following fields: - **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`. - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not `None`). - **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`. - **pixel_mask** -- Pixel mask to be fed to a model. Returned when `images` is not `None`. tokenizer_init_kwargsrzAInvalid input text. Please provide a string, or a list of stringsrr num_cropsr)data) _merge_kwargsrr' init_kwargs isinstancestrlist ValueErrorr&r) pixel_valuesshapepopreplace image_tokenappendr) r4r8r9audiovideosr: output_kwargs image_inputstokens_per_imageprompt_stringsr>sample text_inputss r"__call__zAriaProcessor.__call__Ps^<+**  "&.."<"<  dC 6DD$' 47C0H`a a  /4//0L $33L4M4M4S4STU4VW N$((58HHI .(B(BDNND^D^ajDjk%%f- . L!N$dnn  M* !@K!@)r'model_input_namesr&rDdictfromkeys)r4tokenizer_input_namesimage_processor_input_namesnames r"r\zAriaProcessor.model_input_namesse $ @ @&*&:&:&L&L#9T&kW[_jWjt&k#&kDMM"7:U"UVWW'ls A#A#)NNNN)NNN)rrr__doc__ attributes valid_kwargsimage_processor_classtokenizer_classrrrCrrfloatr/r3rr rr r rrrTrVrZpropertyr\ __classcell__)r7s@r"r%r%,s $[1J#%67L0%O/3'+BF R+,R } R "$uUCZ'8#'=">? R&(, =BI0$y/4HYCZZ[=B$=B ,- =B =B~<6XXr!r%N)typingrrrrimage_processing_utilsr image_utilsr processing_utilsr r r tokenization_utilsr rutilsrautorrr%__all__r r!r"rrsL*/.2%HH>  *% yXNyXx  r!