rho(dZddlmZmZddlZddlmZddlm Z ddl m Z m Z m Z mZmZddlmZmZGd d ed ZGd de d ZGdde ZdgZy)z Processor class for Chameleon. )OptionalUnionN) BatchFeature) ImageInput)MultiModalDataProcessingKwargsProcessorMixin TextKwargsUnpack)PreTokenizedInput TextInputceZdZUeed<y)ChameleonTextKwargsreturn_for_text_completionN)__name__ __module__ __qualname__bool__annotations__/var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/transformers/models/chameleon/processing_chameleon.pyrr#s $$rrF)totalc.eZdZUeed<ddddddidZy)ChameleonProcessorKwargs text_kwargsF)paddingrreturn_mm_token_type_idsreturn_tensorspt)r common_kwargsN)rrrrr _defaultsrrrrr's+$$*/(- d Irrc eZdZdZddgZdZdZddedeffd Z dd e e d e e e eee eefd eed efd ZddZdZdZedZxZS)ChameleonProcessora/ Constructs a Chameleon processor which wraps a Chameleon image processor and a Chameleon tokenizer into a single processor. [`ChameleonProcessor`] offers all the functionalities of [`ChameleonImageProcessor`] and [`LlamaTokenizerFast`]. See the [`~ChameleonProcessor.__call__`] and [`~ChameleonProcessor.decode`] for more information. Args: image_processor ([`ChameleonImageProcessor`]): The image processor is a required input. tokenizer ([`LlamaTokenizerFast`]): The tokenizer is a required input. image_seq_length (`int`, *optional*, defaults to 1024): Sequence length of one image embedding. image_token (`str`, *optional*, defaults to `""`): The special token used to indicate image in the text. image_processor tokenizer)LlamaTokenizerLlamaTokenizerFastChameleonImageProcessorimage_seq_length image_tokenc>||_t|dr |jn||_|j|j|_t|dr |j nd|_t|dr |jnd|_|j|j|_|j|j |_ |j|j|_ |j|j|jg|_ t|5||y)Nr, boi_tokenz eoi_tokenz)r+hasattrr,convert_tokens_to_idsimage_token_idr.image_start_tokenr/image_end_tokenimage_start_token_idimage_end_token_id image_idssuper__init__)selfr&r'r+r, __class__s rr9zChameleonProcessor.__init__Ls 04;I}4U900[f'==d>N>NO#*9k#BI   7>i6Uy22[c'==d>N>NO$-$C$CDDZDZ$[!"+"A"A$BVBV"W--t/H/H$JaJab )4rimagestextkwargsreturnc t|tr|g}n.t|tst|dts td| | t d|j t fd|jji|}|djdd}g}|j|j|jzz|jz} |D]J} | j|j| } |s| |jjz } |j!| Li} ||j"|fi|d } |djd d} |djd d} |j|fi|dd di}|j%||d g | rft'j(|d}t'j*|d}d|t'j,||j.<|j1|d<t3i|| | 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 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`. rzAInvalid input text. Please provide a string, or a list of stringsNz&You must provide either text or imagestokenizer_init_kwargsrrF images_kwargsr rimage) modalities input_idsmm_token_type_ids)data tensor_type) isinstancestrlist TypeError ValueError _merge_kwargsrr' init_kwargspopr3r,r+r4replace sep_tokenappendr&_check_special_mm_tokensnparray zeros_likeisinr7tolistr)r:r<r=audiovideosr> output_kwargsrprompt_stringsone_img_tokenssample image_inputsr r text_inputs array_idsrGs r__call__zChameleonProcessor.__call__[sR dC 6DD$' 47C0H_` `  vision_datargrhs r_get_num_multimodal_tokensz-ChameleonProcessor._get_num_multimodal_tokenssb  " $ 5 5 9:S=MM !"c+&6 6    4D[lm n, ,,rc:|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_decoder:argsr>s rrozChameleonProcessor.batch_decodes +t~~**D;F;;rc:|jj|i|S)z This method forwards all its arguments to LlamaTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )r'decoderps rrszChameleonProcessor.decodes %t~~$$d5f55rc|jj}|jj}ttj ||zSN)r'model_input_namesr&rLdictfromkeys)r:tokenizer_input_namesimage_processor_input_namess rrvz$ChameleonProcessor.model_input_namessA!% @ @&*&:&:&L&L#DMM"7:U"UVWWr)iz)NNNNru)rrr__doc__ attributestokenizer_classimage_processor_classintrKr9rrrrr rLr rrrdrmrorspropertyrv __classcell__)r;s@rr%r%5s$$[1J>O5 5S 5^a 5"(,hl O^$O^uY(94 ?DQbLccdeO^ 12 O^ O^b-0<6XXrr%)r{typingrrnumpyrVfeature_extraction_utilsr image_utilsrprocessing_utilsrr r r r tokenization_utils_baser rrrr%__all__rrrrs`#4%D%*E% /u cXcXL r