a hD@sdZddlmZmZddlZddlmZddlm Z m Z ddl m Z m Z mZmZddlmZmZGd d d e d d ZGd dde d d ZeeeeeedddZeeeeeeeeeejdddZeeeedddZGdddeZdgZdS)zProcessor class for Mllama.)OptionalUnionN) BatchFeature) ImageInputmake_nested_list_of_images) ImagesKwargsProcessingKwargsProcessorMixinUnpack)PreTokenizedInput TextInputc@seZdZUeeed<dS)MllamaImagesKwargsmax_image_tilesN)__name__ __module__ __qualname__rint__annotations__rrh/var/www/html/assistant/venv/lib/python3.9/site-packages/transformers/models/mllama/processing_mllama.pyrs rF)totalc@s"eZdZUeed<dddiiZdS)MllamaProcessorKwargs images_kwargsZ image_kwargsrN)rrrrr _defaultsrrrrr s r) input_idsimage_token_idreturncsfddt|D}t|dkr&gSt|dkr@|ddggSddt|dd|ddD}||dt|g|dd}|dddD](}|d|ddkr||d<|d}q|S)a Generate a cross-attention token mask for image tokens in the input sequence. This function identifies the positions of image tokens in the input sequence and creates a mask that defines which subsequent tokens each image token should attend to. Args: input_ids (list[int]): A list of token ids representing the input sequence. image_token_id (int): The id of the token used to represent images in the sequence. Returns: list[list[int]]: A list of [start, end] pairs, where each pair represents the range of tokens an image token should attend to. Notes: - If no image tokens are present, an empty list is returned. - For a single image token, it attends to all subsequent tokens until the end of the sequence. - For multiple image tokens, each attends to tokens up to the next image token or the end of the sequence. - Consecutive image tokens are treated as a group and attend to all subsequent tokens together. csg|]\}}|kr|qSrr).0itokenrrr @z2get_cross_attention_token_mask..rcSsg|]\}}||gqSrr)rZloc1Zloc2rrrr#Ir$N) enumeratelenzipappend)rrZimage_token_locationsZ vision_masksZ last_mask_endZ vision_maskrr"rget_cross_attention_token_mask*s  $  r+)cross_attention_token_mask num_tiles max_num_tileslengthrc Cst|}tdd|D}tj||||ftjd}tt||D]j\}\}} tt|| D]N\} \} } t| dkrZ| \} }t||}|dkr|}d||| || d| f<qZq@|S)a Convert the cross attention mask indices to a cross attention mask 4D array. This function takes a sparse representation of cross attention masks and converts it to a dense 4D numpy array. The sparse representation is a nested list structure that defines attention ranges for each image in each batch item. Args: cross_attention_token_mask (list[list[list[int]]]): A nested list structure where: - The outer list represents the batch dimension. - The middle list represents different images within each batch item. - The inner list contains pairs of integers [start, end] representing token ranges for each image. num_tiles (list[list[int]]): A nested list structure specifying the number of tiles for each image in each batch item. max_num_tiles (int): The maximum possible number of tiles. length (int): The total sequence length of the input. Returns: np.ndarray: A 4D numpy array of shape (batch_size, length, max_num_images, max_num_tiles) The array contains `1` where attention is allowed and `0` where it is not. Note: - Special handling is done for cases where the end token is -1, which is interpreted as attending to the end of the sequence. cSsg|] }t|qSrr()rZmasksrrrr#xr$z@convert_sparse_cross_attention_mask_to_dense..)shapeZdtyper&r%N)r(maxnpZzerosZint64r'r)min)r,r-r.r/Z batch_sizeZmax_num_imagescross_attention_maskZ sample_idxZ sample_masksZsample_num_tilesZmask_idx locationsZmask_num_tilesstartendrrr,convert_sparse_cross_attention_mask_to_denseZs   r:)prompt bos_token image_tokenrcCsH||vr |Sd}||r4|t|d}|d7}q||||S)a\ Builds a string from the input prompt by adding `bos_token` if not already present. Args: prompt (`str`): The input prompt string. bos_token (`str`): The beginning of sentence token to be added. image_token (`str`): The image token used to identify the start of an image sequence. Returns: str: The modified prompt string with the `bos_token` added if necessary. Examples: >>> build_string_from_input("Hello world", "", "<|image|>") 'Hello world' >>> build_string_from_input("<|image|>Hello world", "", "<|image|>") '<|image|>Hello world' >>> build_string_from_input("Hello world", "", "<|image|>") 'Hello world' rNr%) startswithr()r;r<r=Znum_image_tokens_on_startrrrbuild_string_from_inputs  r?c s~eZdZdZddgZdZdZdfdd Zdee ee e e e e e e feeed d d ZdddZeddZZS)MllamaProcessora Constructs a Mllama processor which wraps [`MllamaImageProcessor`] and [`PretrainedTokenizerFast`] into a single processor that inherits both the image processor and tokenizer functionalities. See the [`~MllamaProcessor.__call__`] and [`~OwlViTProcessor.decode`] for more information. The preferred way of passing kwargs is as a dictionary per modality, see usage example below. ```python from transformers import MllamaProcessor from PIL import Image processor = MllamaProcessor.from_pretrained("meta-llama/Llama-3.2-11B-Vision") processor( images=your_pil_image, text=["<|image|>If I had to write a haiku for this one"], images_kwargs = {"size": {"height": 448, "width": 448}}, text_kwargs = {"padding": "right"}, common_kwargs = {"return_tensors": "pt"}, ) ``` Args: image_processor ([`MllamaImageProcessor`]): The image processor is a required input. tokenizer ([`PreTrainedTokenizer`, `PreTrainedTokenizerFast`]): 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. image_processor tokenizerZMllamaImageProcessorZPreTrainedTokenizerFastNcsbt|ds d|_||j|_n|j|_|j|_d|_||j|_|j|_tj|||ddS)Nr=z <|image|>z<|python_tag|>) chat_template) hasattrr=Zconvert_tokens_to_idsrZ python_tokenZpython_token_idr<super__init__)selfrArBrC __class__rrrFs zMllamaProcessor.__init__)imagestextkwargsrc s|dur|durtdjtfdjji|}|d}d|d<|d}|d} i} |durt|trr|g}n(t|ttfrt dd |Dstd fd d |D} fd d |D}| dd} j|fi|} j || dgdfdd | dD}| | dg}|dur@j |}t|}dd |D}|durtdd | Drzt dd | Dsztdt| dkr|| ks||kr|durtdnNd}t|t| kr|| krd}n||krd}td| d|d||dur.j |fi|}| d}| ||dur|durfdd | dD}t||j jtd d | dDd!}|| d"<| dd}t| |d#}|S)$a& Main method to prepare text(s) and image(s) to be fed as input to the model. This method forwards the `text` arguments to PreTrainedTokenizerFast's [`~PreTrainedTokenizerFast.__call__`] if `text` is not `None` to encode the text. To prepare the image(s), this method forwards the `images` arguments to MllamaImageProcessor's [`~MllamaImageProcessor.__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`. TODO: add aspect_ratio_ids and aspect_ratio_mask and cross_attention_mask Nz'You must specify either text or images.Ztokenizer_init_kwargs text_kwargsreturn_tensorsr common_kwargscss|]}t|tVqdSN) isinstancestrrtrrr r$z+MllamaProcessor.__call__..zAInvalid input text. Please provide a string, or a list of stringscsg|]}|jqSr)countr=rSrGrrr#r$z,MllamaProcessor.__call__..csg|]}t|jjqSr)r?r<r=)rZ text_itemrWrrr#r$Z padding_sideimage)Z modalitiescsg|]}|jqSr)rVrrZ token_idsrWrrr# r$rrcSsg|] }t|qSrr0)rsamplerrrr#'r$css|]}|dkVqdS)rNr)rZ batch_imgrrrrU*r$zaIf a batch of text is provided, there should be either no images or at least one image per samplez@No image were provided, but there are image tokens in the promptzZMake sure to pass your images as a nested list, where each sub-list holds images per batchzhIf you activated truncation with `max_length`, increase the `max_length` so image tokens aren't cropped.z)The number of image tokens in each text (zA) should be the same as the number of provided images per batch (z). r-csg|]}t|jqSr)r+rrYrWrrr#Hscss|]}t|VqdSrPr0)rrrrrrUOr$)r-r.r/r6)dataZ tensor_type) ValueErrorZ _merge_kwargsrrBZ init_kwargsrQrRlisttupleallpopZ_check_special_mm_tokensupdaterAZ fetch_imagesranysumr:rr3r)rGrJrKZaudioZvideosrLZ output_kwargsrMrrOr\Zn_images_in_text_encodingZn_images_in_idsZn_images_in_imagesZ add_messageZimage_featuresr-r,r6rNZ batch_featurerrWr__call__s'                  zMllamaProcessor.__call__TFcKs|jj|f||d|S)a Post-process the output of the model to decode the text. Args: generated_outputs (`torch.Tensor` or `np.ndarray`): The output of the model `generate` function. The output is expected to be a tensor of shape `(batch_size, sequence_length)` or `(sequence_length,)`. skip_special_tokens (`bool`, *optional*, defaults to `True`): Whether or not to remove special tokens in the output. Argument passed to the tokenizer's `batch_decode` method. clean_up_tokenization_spaces (`bool`, *optional*, defaults to `False`): Whether or not to clean up the tokenization spaces. Argument passed to the tokenizer's `batch_decode` method. **kwargs: Additional arguments to be passed to the tokenizer's `batch_decode method`. Returns: `list[str]`: The decoded text. )skip_special_tokensclean_up_tokenization_spaces)rBZ batch_decode)rGZgenerated_outputsrhrirLrrrpost_process_image_text_to_textXsz/MllamaProcessor.post_process_image_text_to_textcCs0|jj}|jj}dd|D}t||dgS)NcSsg|]}|dkr|qS)r-r)rnamerrrr#zr$z5MllamaProcessor.model_input_names..r6)rBmodel_input_namesrAr^)rGZtokenizer_input_namesZimage_processor_input_namesrrrrlssz!MllamaProcessor.model_input_names)N)NNNN)TF)rrr__doc__ attributesZimage_processor_classZtokenizer_classrFrrrr r r^r rrrgrjpropertyrl __classcell__rrrHrr@s& y r@)rmtypingrrnumpyr4Zfeature_extraction_utilsrZ image_utilsrrZprocessing_utilsrr r r Ztokenization_utils_baser r rrr^rr+Zndarrayr:rRr?r@__all__rrrrs&  1  0%P