`iD zdZddlmZmZddlZddlmZddlm Z m Z ddl m Z m Z mZmZddlmZmZGd d e d ZGd de d ZdeededeeefdZdeeeedeeedededejf dZdedededefdZGddeZdgZdS)zProcessor class for Mllama.)OptionalUnionN) BatchFeature) ImageInputmake_nested_list_of_images) ImagesKwargsProcessingKwargsProcessorMixinUnpack)PreTokenizedInput TextInputc&eZdZUeeed<dS)MllamaImagesKwargsmax_image_tilesN)__name__ __module__ __qualname__rint__annotations__/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/mllama/processing_mllama.pyrrs"c]"""""rrF)totalc&eZdZUeed<dddiiZdS)MllamaProcessorKwargs images_kwargs image_kwargsrN)rrrrr _defaultsrrrrr s2%%%%  q IIIrr input_idsimage_token_idreturncfdt|D}t|dkrgSt|dkr |ddggSdt|dd|ddD}||dt|g|dd}|dddD]$}|d|ddz kr||d<|d}%|S)a Generate a cross-attention token mask for image tokens in the input sequence. This function identifies the positions of image tokens in the input sequence and creates a mask that defines which subsequent tokens each image token should attend to. Args: input_ids (list[int]): A list of token ids representing the input sequence. image_token_id (int): The id of the token used to represent images in the sequence. Returns: list[list[int]]: A list of [start, end] pairs, where each pair represents the range of tokens an image token should attend to. Notes: - If no image tokens are present, an empty list is returned. - For a single image token, it attends to all subsequent tokens until the end of the sequence. - For multiple image tokens, each attends to tokens up to the next image token or the end of the sequence. - Consecutive image tokens are treated as a group and attend to all subsequent tokens together. c&g|] \}}|k |Srr).0itokenr"s r z2get_cross_attention_token_mask..@s(___81euP^G^G^QG^G^G^rrcg|] \}}||g Srr)r&loc1loc2s rr)z2get_cross_attention_token_mask..Is nnnZT4T4LnnnrN) enumeratelenzipappend)r!r"image_token_locations vision_masks last_mask_end vision_masks ` rget_cross_attention_token_maskr7*s",`___y/C/C___ !!Q&&  !!Q&&&q)2.//nn37LSbS7QShijikikSl3m3mnnnL.r2C NNCDDD !$Q'M#DDbD)'' q>[^a/ / /*KN#A rcross_attention_token_mask num_tiles max_num_tileslengthc t|}td|D}tj||||ftj}t t ||D]k\}\}} t t || D]E\} \} } t| dkr*| \} }t||}|dkr|}d||| || d| f<Fl|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. c34K|]}t|VdSNr0)r&maskss r z?convert_sparse_cross_attention_mask_to_dense..xs(LLULLLLLLr)shapedtyper+r*N)r0maxnpzerosint64r/r1min)r8r9r:r; batch_sizemax_num_imagescross_attention_mask sample_idx sample_maskssample_num_tilesmask_idx locationsmask_num_tilesstartends r,convert_sparse_cross_attention_mask_to_denserUZs:/00JLL1KLLLLLN86>=Ah 9B#F`bkBlBl8m8m[[4 4\#35>s>> 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*) startswithr0)rVrWrXnum_image_tokens_on_starts rbuild_string_from_inputr\s4F !   K ( ('K((**+!Q&!   K ( ('55 Jy J& J JJrc eZdZdZddgZdZdZdfd Z ddee d ee e e e e e e fd eed efd Z ddZedZxZS)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 tokenizerMllamaImageProcessorPreTrainedTokenizerFastNcRt|ds'd|_||j|_n|j|_|j|_d|_||j|_|j|_t|||dS)NrXz <|image|>z<|python_tag|>) chat_template) hasattrrXconvert_tokens_to_idsr" python_tokenpython_token_idrWsuper__init__)selfr_r`rd __class__s rrjzMllamaProcessor.__init__sy-00 ;*D "+"A"A$BR"S"SD  (4D "+":D ,(>>t?PQQ", )=QQQQQrimagestextkwargsr#c ||tdjtfdjji|}|d}d|d<|d}|d} i} |t |t r|g}nDt |ttfrtd|Dstd fd |D} fd |D}| d d} j|fi|} || d gfd| dD}| | dg}|5j |}t|}d|D}|t!d| Dr(td| Dstdt#| dkrh|| ks||kr\|tdd}t#|t#| kr || krd}n||krd}td| d|d||8j |fi|}| d}| ||U|Sfd| dD}t%||j jt)d| dD }|| d!<| dd}t+| |"}|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.tokenizer_init_kwargs text_kwargsreturn_tensorsr common_kwargsc3@K|]}t|tVdSr>) isinstancestr)r&ts rrAz+MllamaProcessor.__call__..s-=_=_UVjC>P>P=_=_=_=_=_=_rzAInvalid input text. Please provide a string, or a list of stringscDg|]}|jSr)countrX)r&rxrks rr)z,MllamaProcessor.__call__..s(HHHa(8 9 9HHHrcFg|]}t|jjSr)r\rWrX)r& text_itemrks rr)z,MllamaProcessor.__call__..s,ooo]f+It~tGWXXooor padding_sideimage) modalitiescDg|]}|jSr)rzr"r& token_idsrks rr)z,MllamaProcessor.__call__.. s(kkk yt/BCCkkkrr!rc,g|]}t|Srr?)r&samples rr)z,MllamaProcessor.__call__..'s!C!C!C&#f++!C!C!Crc3"K|] }|dkV dSrNrr& batch_imgs rrAz+MllamaProcessor.__call__..*s&DDi9>DDDDDDrc3"K|] }|dkV dSrrrs rrAz+MllamaProcessor.__call__..*s?QQ#, QQQQQQQrzaIf 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). r9c:g|]}t|jSr)r7r"rs rr)z,MllamaProcessor.__call__..Hs4***S\.y$:MNN***rc34K|]}t|VdSr>r?)r&r!s rrAz+MllamaProcessor.__call__..Os(QQi3y>>QQQQQQr)r9r:r;rL)data tensor_type) ValueError _merge_kwargsrr` init_kwargsrvrwlisttupleallpop_check_special_mm_tokensupdater_ fetch_imagesranysumrUrrEr)rkrmrnaudiovideosro output_kwargsrrrrtrn_images_in_text_encodingn_images_in_idsn_images_in_images add_messageimage_featuresr9r8rLrs batch_features` r__call__zMllamaProcessor.__call__s%N >F/77F!C!CF!C!C!C   DD3CDDDDD SQQ0@QQQNN !w#$$q(("&666/M_:_:_>$%ghhh"$K-..#6F2G2GGGL^brLrLr'C (,>>>'Q $eDTee@ReeWbee  1T1&JJMJJN&**;77I KK ' ' '  $"2****`hit`u*** &$P*#"2BQQ8K;PQQQQQ $$$ ,@D' (&**+;TBB$$NKKK rTFc .|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)r` batch_decode)rkgenerated_outputsrrros rpost_process_image_text_to_textz/MllamaProcessor.post_process_image_text_to_textXs:(+t~*  3)E      rcv|jj}|jj}d|D}t||zdgzS)Ncg|] }|dk| S)r9r)r&names rr)z5MllamaProcessor.model_input_names..zs$&k&k&kW[_jWjWjtWjWjWjrrL)r`model_input_namesr_r)rktokenizer_input_namesimage_processor_input_namess rrz!MllamaProcessor.model_input_namesssO $ @&*&:&L#'l&k8S&k&k&k#),GGKaJbbcccrr>)NNNN)TF)rrr__doc__ attributesimage_processor_classtokenizer_classrjrrrrr rr rrrrpropertyr __classcell__)rls@rr^r^s!>$[1J2/O R R R R R R(,hl vv$vuY(94 ?DQbLccdev ./ v vvvvrY^    6ddXdddddrr^)rtypingrrnumpyrFfeature_extraction_utilsr image_utilsrrprocessing_utilsr r r r tokenization_utils_baser rrrrrr7ndarrayrUrwr\r^__all__rrrrs "!""""""""444444AAAAAAAAVVVVVVVVVVVVCCCCCCCC#####U####,E-d3i--QUVZ[^V_Q`----`- $T$s)_ 5- DI- -   - Z - - - - `"KC"KC"Kc"Kc"K"K"K"KJLdLdLdLdLdnLdLdLd^  r