g2dZddlmZmZddlmZddlmZmZm Z ddl m Z m Z m Z mZddlmZmZddlmZmZmZmZmZejeZGd d e d Zd efdZdZGddeZGdde Z dS)z Processor class for Pixtral. )ListUnion) BatchFeature) ImageInputis_valid_image load_image)ProcessingKwargsProcessorMixinUnpack!_validate_images_text_input_order)PreTokenizedInput TextInput)is_torch_deviceis_torch_dtypeis_torch_tensorloggingrequires_backendsc"eZdZddiiddidZdS)PixtralProcessorKwargspaddingFreturn_tensorspt) text_kwargs images_kwargs common_kwargsN)__name__ __module__ __qualname__ _defaultsj/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/pixtral/processing_pixtral.pyrrs5 u  d IIIr"rF)totalreturncVt|to|dS)Nhttp) isinstancestr startswith)vals r#is_urlr,,s# c3   :CNN6$:$::r"c>t|pt|SN)r,r)elems r#is_image_or_image_urlr01s $<< />$///r"ceZdZddZdS)BatchMixFeaturer%ct|dgddl}i}d}|tdkrtd}t |rn\t |t s$t|st |tr|}n tdt |d| D]\}}t |trfd|D||<-t ||j r&| |r|ji||<ht ||j r|||||<|||<||_|S) a  Send all values to device by calling `v.to(*args, **kwargs)` (PyTorch only). This should support casting in different `dtypes` and sending the `BatchFeature` to a different `device`. Args: args (`Tuple`): Will be passed to the `to(...)` function of the tensors. kwargs (`Dict`, *optional*): Will be passed to the `to(...)` function of the tensors. Returns: [`BatchFeature`]: The same instance after modification. torchrNdevicez*Attempting to cast a BatchFeature to type z. This is not supported.cRg|]#}|D]}t||ji$Sr!)rto).0sampleelementargskwargss r# z&BatchMixFeature.to..Zs]4:vDKYhipYqYqGJ///r")r5)rr4getlenrr(r)rint ValueErroritemslistTensoris_floating_pointr7data) selfr;r<r4new_datar5argkvs `` r#r7zBatchMixFeature.to7s $ *** H%% >c$ii!mmq'Cc"" rC%% r)=)= rCQTAUAU r!!pcRUhh!p!p!pqqqJJLL DAq!T"" >? Au|,, 1H1H1K1K "adD3F33 Au|,, 1Cdd&d11    r"N)r%r2)rrrr7r!r"r#r2r26s(......r"r2c eZdZdZddgZgdZdZdZ dd effd Z dde de e e ee ee fdeedefdZdZdZedZxZS)PixtralProcessora 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. 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_size image_tokenimage_break_tokenimage_end_tokenAutoImageProcessor AutoTokenizerN[IMG] [IMG_BREAK] [IMG_END]rQc ||_||_||_||_t |||dS)N)rP)rQrRrSrTsuper__init__) rGrNrOrQrPrRrSrTr< __class__s r#r]zPixtralProcessor.__init__sI%&!2. )=QQQQQr"imagestextr<r%c pt||\}}|jtfd|jji|}|t |r|gg}nt |trt |dr|g}nZt |tsEt |dts*t |ddstdd|D}|j |fd|j i|d}ni}t |tr|g}n?t |ts*t |dtstd|}| d %|d }| d } g}t|| |D]\} } } g} t| | D]\}}|\}}||j z}||j z}|jg|z|jgzg|z}d |D}|j|d <d |}| || |jdd} d| vr0| d}| d|d} d| v0|| |j|fi|d}t+i||S)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 doctsring 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_kwargsNrzdInvalid input images. Please provide a single image or a list of images or a list of list of images.c&g|]}d|DS)c,g|]}t|Sr!)r )r8ims r#r=z8PixtralProcessor.__call__...s777"z"~~777r"r!)r8r9s r#r=z-PixtralProcessor.__call__..s'MMMF77777MMMr"rQrzAInvalid input text. Please provide a string, or a list of strings pixel_values image_sizescg|] }|D]}| Sr!r!)r8sublistitems r#r=z-PixtralProcessor.__call__..s&%]%]%]wU\%]%]Td%]%]%]%]r"z r)rF)r _merge_kwargsrrO init_kwargsr0r(rCrArNrQr)r>popziprRrSrTjoinappendreplacer2)rGr_r`audiovideosr< output_kwargs image_inputsprompt_stringsrg sample_imagessample_image_sizesr9replace_stringsimage image_sizeheightwidthnum_height_tokensnum_width_tokensreplace_tokens replace_str text_inputss r#__call__zPixtralProcessor.__call__sWR9FF ** "  "&."<    $V,, !(FD)) .CF1I.N.N  vt,, "6!9d33 .fQil;;  !zNMfMMMF/4/uu4?uVcdsVtuuLLL dC  b6DDD$'' b 47C0H0H b`aa a   N + + 7!.1F&**=99KN=@VZ=[=[ . .9 16"$),]rs444444AAAAAAAAAAkkkkkkkkkkkkCCCCCCCCaaaaaaaaaaaaaa  H % %     -U    ;4;;;; 000 /////l///drXrXrXrXrX~rXrXrXrXrXr"