o wi @sdZddlmZddlmZddlmZddlmZm Z m Z m Z ddl m Z mZddlmZeeZd ZGd d d e d d ZGddded d ZGddde ZdgZdS)z Processor class for Janus. )Union) BatchFeature) ImageInput)ProcessingKwargsProcessorMixin TextKwargsUnpack)PreTokenizedInput TextInput)loggingzYou are a helpful language and vision assistant. You are able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language. c@seZdZUeed<dS)JanusTextKwargsgeneration_modeN)__name__ __module__ __qualname__str__annotations__rrg/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/transformers/models/janus/processing_janus.pyr %s r F)totalc@s*eZdZUeed<dddddidZdS) JanusProcessorKwargs text_kwargsFtext)paddingrreturn_tensorspt)r common_kwargsN)rrrr r _defaultsrrrrr)s  rc seZdZdZddgZdZdZdfdd Z    dd ee e e e e e fd e d e ed efddZddZddZd e fddZeddZZS)JanusProcessora7 Constructs a Janus processor which wraps a Janus Image Processor and a Llama tokenizer into a single processor. [`JanusProcessor`] offers all the functionalities of [`JanusImageProcessor`] and [`LlamaTokenizerFast`]. See the [`~JanusProcessor.__call__`] and [`~JanusProcessor.decode`] for more information. Args: image_processor ([`JanusImageProcessor`]): The image processor is a required input. tokenizer ([`LlamaTokenizerFast`]): 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. use_default_system_prompt (`str`, *optional*, defaults to `False`): Use default system prompt for Text Generation. image_processor tokenizerJanusImageProcessorLlamaTokenizerFastNFc s:d|_|j|_|j|_|j|_||_tj|||ddS)Ni@) chat_template) num_image_tokens image_token boi_tokenimage_start_token eoi_tokenimage_end_tokenuse_default_system_promptsuper__init__)selfr r!r$r+kwargs __class__rrr-Gs zJanusProcessor.__init__rimagesr/returnc Ks8|jtfd|jji|}|dur|durtd|dur:t|tr&|g}nt|ttfr6t dd|Ds:td|d d}g}|j |j |j |j} |D]"} | |j | } |jre|d kret| } |d krn| |j 7} || qQ|j|fi|d} |dur|d kr|jdd |i|d d | d <t| dS)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 JanusImageProcessor's [`~JanusImageProcessor.__call__`] if `images` is not `None`. Please refer to the doctsring of the above two methods for more information. Args: 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). 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. 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`. tokenizer_init_kwargsNz'You must specify either text or images.css|]}t|tVqdSN) isinstancer).0trrr sz*JanusProcessor.__call__..zAInvalid input text. Please provide a string, or a list of stringsrrrimager2 images_kwargs pixel_values)datar) _merge_kwargsrr! init_kwargs ValueErrorr6rlisttupleallpopr(r&r%r*replacer+DEFAULT_SYSTEM_PROMPTappendr r) r.rr2videosaudior/ output_kwargsrprompt_stringsone_img_tokenspromptr=rrr__call__Ps<(     zJanusProcessor.__call__cO|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/rrrrPzJanusProcessor.batch_decodecOrO)z This method forwards all its arguments to LlamaTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )r!decoderQrrrrTrSzJanusProcessor.decodecKs|jj|fi|S)z Forwards all arguments to the image processor's `postprocess` method. Refer to the original method's docstring for more details. )r postprocess)r.r2r/rrrrUszJanusProcessor.postprocesscCs"|jj}|jj}tt||Sr5)r!model_input_namesr rAdictfromkeys)r.tokenizer_input_namesimage_processor_input_namesrrrrVsz JanusProcessor.model_input_names)NF)NNNN)rrr__doc__ attributesimage_processor_classtokenizer_classr-rr r rArr rrrNrPrTrUpropertyrV __classcell__rrr0rr1s0  LrN)r[typingrfeature_extraction_utilsr image_utilsrprocessing_utilsrrrr tokenization_utils_baser r utilsr get_loggerrloggerrFr rr__all__rrrrs