rh+dZddlmZddlZddlmZddlmZm Z m Z ddl m Z m Z mZmZddlmZmZdd lmZej*eZGd d e d ZGddeZdgZy)z Processor class for Llava. )UnionN) BatchFeature) ImageInputget_image_sizeto_numpy_array)MultiModalDataProcessingKwargsProcessorMixinUnpack)PreTokenizedInput TextInput)loggingceZdZdddidZy)LlavaProcessorKwargsF)paddingreturn_mm_token_type_ids) text_kwargs images_kwargsN)__name__ __module__ __qualname__ _defaults}/var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/transformers/models/llava/processing_llava.pyrr&s#(eLIrrF)totalc eZdZdZddgZdZdZ dfd Z ddede e e e e e e fd e ed efd Zdd Zd ZdZedZxZS)LlavaProcessoram Constructs a LLaVa processor which wraps a LLaVa image processor and a LLaMa tokenizer into a single processor. [`LlavaProcessor`] offers all the functionalities of [`LlavaImageProcessor`] and [`LlamaTokenizerFast`]. See the [`~LlavaProcessor.__call__`] and [`~LlavaProcessor.decode`] for more information. Args: image_processor ([`LlavaImageProcessor`], *optional*): The image processor is a required input. tokenizer ([`LlamaTokenizerFast`], *optional*): The tokenizer is a required input. patch_size (`int`, *optional*): Patch size from the vision tower. vision_feature_select_strategy (`str`, *optional*): The feature selection strategy used to select the vision feature from the vision backbone. Should be same as in model's config 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 `""`): Special token used to denote image location. num_additional_image_tokens (`int`, *optional*, defaults to 0): Number of additional tokens added to the image embeddings, such as CLS (+1). If the backbone has no CLS or other extra tokens appended, no need to set this arg. image_processor tokenizerAutoImageProcessor AutoTokenizerc ||_||_||_t|dr |jn||_|j |jdd|_t |!|||y)N image_tokenF)add_special_tokensr) chat_template) patch_sizenum_additional_image_tokensvision_feature_select_strategyhasattrr%encodeimage_token_idsuper__init__) selfr r!r(r*r'r%r)kwargs __class__s rr/zLlavaProcessor.__init__Kso%+F(.L+4;I}4U900[f'..t/?/?TY.Z[\] )=Qrimagestextr1returnc | | td|jtfd|jji|}||j |fi|d}ni}t |tr|g}n.t |tst |dts td|}|jd|d} tt| d\} } | |jz| |jzz|jz} |jdk(r| d z} g}|D]<} | j!|j"|j"| z} |j%| >|d j'd d}|d j'd d }|j|fi|d d di}|j)||dg|rUt+j,|d}t+j.|d}d |||j0k(<|j3|d<t5i|||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`. Nz7You have to specify at least one of `images` or `text`.tokenizer_init_kwargsrrzAInvalid input text. Please provide a string, or a list of strings pixel_valuesdefaultrreturn_tensorsrFimage) modalities input_idsmm_token_type_ids)data tensor_type) ValueError _merge_kwargsrr! init_kwargsr isinstancestrlist TypeErrorgetrrr(r)r*replacer%appendpop_check_special_mm_tokensnparray zeros_liker-tolistr)r0r3r4audiovideosr1 output_kwargs image_inputsprompt_stringsr8heightwidthnum_image_tokenssampler;r text_inputs array_idsr?s r__call__zLlavaProcessor.__call__]sEN >dlVW W***  "&.."<"<   /4//Y-:XYLL dC 6DD$' 47C0H_` `   N + 7'7L*>,q/+JKMFE &$// 9( 00 1 22i? A% N .(8(8$:J:JM]:]^%%f- .'}599:JDQ#0#?#C#CD^`e#f $dnn^i}]7Sidhi  %%nkwi%X #[!9:I " k+.F G BC i4+>+>> ?/@/G/G/IK+ ,!@K!@>PRSM   (%))+t<^@T@T@^@^I,5h,?7ASMN .$// AmW[WfWfFfg   @ @ @ 22i? A% 01C 4DD !"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_decoder0argsr1s rrizLlavaProcessor.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!decoderjs rrmzLlavaProcessor.decodes %t~~$$d5f55rc|jj}|jj}ttj ||zSN)r!model_input_namesr rGdictfromkeys)r0tokenizer_input_namesimage_processor_input_namess rrpz LlavaProcessor.model_input_namessA!% @ @&*&:&:&L&L#DMM"7:U"UVWWr)NNNNNzr)NNNNro)rrr__doc__ attributesimage_processor_classtokenizer_classr/rrrr rGr rrr]rgrirmpropertyrp __classcell__)r2s@rrr-s2$[1J0%O'+$%R("^b U^U^I0$y/4HYCZZ[U^ -. U^ U^n-@<6XXrr)rutypingrnumpyrNfeature_extraction_utilsr image_utilsrrrprocessing_utilsr r r r tokenization_utils_baser rutilsr get_loggerrloggerrr__all__rrrrsl4EE D   H %+5{X^{X|  r