`i#dZddlmZmZddlZddlmZddlm Z ddl m Z m Z m Z mZmZddlmZmZGd d ed ZGd de d ZGdde ZdgZdS)z Processor class for Chameleon. )OptionalUnionN) BatchFeature) ImageInput)MultiModalDataProcessingKwargsProcessorMixin TextKwargsUnpack)PreTokenizedInput TextInputceZdZUeed<dS)ChameleonTextKwargsreturn_for_text_completionN)__name__ __module__ __qualname__bool__annotations__/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/chameleon/processing_chameleon.pyrr#s $$$$$$rrF)totalc0eZdZUeed<ddddddidZdS)ChameleonProcessorKwargs text_kwargsF)paddingrreturn_mm_token_type_idsreturn_tensorspt)r common_kwargsN)rrrrr _defaultsrrrrr'sI$$$$*/(-  d  IIIrrc eZdZdZddgZdZdZdded effd Z dd e e d e e e eee eefdeedefdZddZxZS)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_tokenc8||_t|dr|jn||_||j|_t|dr|jnd|_t|dr|jnd|_||j|_||j|_ ||j|_ |j|j |j g|_ t ||dS)Nr. boi_tokenz eoi_tokenz)r-hasattrr.convert_tokens_to_idsimage_token_idr0image_start_tokenr1image_end_tokenimage_start_token_idimage_end_token_id image_idssuper__init__)selfr&r'r-r. __class__s rr;zChameleonProcessor.__init__Ls  04;I}4U4Uf900[f'==d>NOO#*9k#B#B WI   7>i6U6Ucy22[c'==d>NOO$-$C$CDDZ$[$[!"+"A"A$BV"W"W-t/H$Jab )44444rNimagestextkwargsreturnc t|tr|g}n?t|ts*t|dtstd||t d|jt fd|jji|}|d dd}g}|j |j |j zz|j z} |D]C} | |j | } |s| |jjz } || Di} ||j|fi|d } |d d d} |d d d} |j|fi|dd di}|||d g | rht'j|d}t'j|d}d|t'j||j<||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 `kwargs` 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_kwargspopr5r.r-r6replace sep_tokenappendr&_check_special_mm_tokensnparray zeros_likeisinr9tolistr)r<r>r?audiovideosr@ output_kwargsrprompt_stringsone_img_tokenssample image_inputsr r text_inputs array_idsrIs r__call__zChameleonProcessor.__call__[sgR dC  a6DDD$'' a 47C0H0H a_`` ` O5 5 5S 5^a 5 5 5 5 5 5"(,hl O^O^$O^uY(94 ?DQbLccdeO^ 12 O^ O^O^O^O^b--------rr%)rptypingrrnumpyrXfeature_extraction_utilsr image_utilsrprocessing_utilsrr r r r tokenization_utils_baser rrrr%__all__rrrr}s^#"""""""444444%%%%%%DCCCCCCC%%%%%*E%%%%     /u    L-L-L-L-L-L-L-L-^ r