o Zh+@sdZddlmZmZddlmZddlmZmZm Z ddl m Z m Z m Z mZddlmZmZddlmZeeZGd d d e d d Zd efddZddZGddde ZdgZdS)z Processor class for Pixtral. )ListUnion) BatchFeature) ImageInputis_valid_image load_image)ProcessingKwargsProcessorMixinUnpack!_validate_images_text_input_order)PreTokenizedInput TextInput)loggingc@s eZdZddiiddidZdS)PixtralProcessorKwargspaddingFreturn_tensorspt) text_kwargs images_kwargsZ common_kwargsN)__name__ __module__ __qualname__ _defaultsrr]/var/www/auris/lib/python3.10/site-packages/transformers/models/pixtral/processing_pixtral.pyrs rF)totalreturncCst|to |dS)Nhttp) isinstancestr startswith)valrrris_url,sr#cCst|pt|SN)r#r)elemrrris_image_or_image_url1sr&c seZdZdZddgZgdZdZdZ     dd edeffdd Z    dde de e e ee ee fdeedefddZddZddZeddZZS)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_tokenZAutoImageProcessorZ AutoTokenizerN[IMG] [IMG_BREAK] [IMG_END]r+r,c  sB||_||_||_||j|_||_||_tj|||ddS)N)r*) r+r,r-Zconvert_tokens_to_idsZimage_token_idr.r/super__init__) selfr(r)r+r,r*r-r.r/kwargs __class__rrr6[s zPixtralProcessor.__init__imagestextr8rcKsDt||\}}|jtfd|jji|}|j|j}|durmt|r&|g}n2t|t t fr4t|dr4n$t|t t frTt|dt t frTt|ddrTdd|D}nt ddd|D}|j |fd|i|d }ni}t|t rx|g}nt|t st|dt st d |} |d durt|d } g} g} |D]^} |j| vrt| \} }| |}||}|jg||jgg|}d d|D}|j|d<d|}| || |jdd} |j| vsd| vr| d}| d|d} d| vs| | q|ddd}|j| fi|d}|j| |dgdti|||dS)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`. Ztokenizer_init_kwargsNrcSg|] }|D]}|qqSrr).0sublistimagerrr z-PixtralProcessor.__call__..zdInvalid input images. Please provide a single image, a list of images, or a list of lists of images.cSs"g|] }t|tr t|n|qSr)rr r)r>ZimrrrrAs"r+rzAInvalid input text. Please provide a string, or a list of stringsZ pixel_values image_sizescSr=rr)r>r?itemrrrrArBz r1rrr@)Z modalities)dataZ tensor_type)r Z _merge_kwargsrr)Z init_kwargsr+r,r&rlisttuple ValueErrorr(r getiterr-nextr.r/joinappendreplacepopZ_check_special_mm_tokensr)r7r;r<ZaudioZvideosr8Z output_kwargsr+Z image_inputsZprompt_stringsrCZreplace_stringssampleheightwidthZnum_height_tokensZnum_width_tokensZreplace_tokensZ replace_strrZ text_inputsrrr__call__osx)            zPixtralProcessor.__call__cO|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. )r) batch_decoder7argsr8rrrrWzPixtralProcessor.batch_decodecOrV)z This method forwards all its arguments to LlamaTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )r)decoderXrrrr[rZzPixtralProcessor.decodecCs"|jj}|jj}tt||Sr$)r)model_input_namesr(rHdictfromkeys)r7Ztokenizer_input_namesZimage_processor_input_namesrrrr\sz"PixtralProcessor.model_input_names)NNr0r1Nr2r3r4)NNNN)rrr__doc__ attributesZ valid_kwargsZimage_processor_classZtokenizer_classintr6rrrr rr rrrUrWr[propertyr\ __classcell__rrr9rr'5sH nr'N)r_typingrrZfeature_extraction_utilsrZ image_utilsrrrZprocessing_utilsr r r r Ztokenization_utils_baser rutilsrZ get_loggerrloggerrboolr#r&r'__all__rrrrs     @