tj#dZddlmZddlmZddlmZmZmZm Z m Z ddl m Z m Z ddlmZGdde d ZGd d ed ZeGd deZdgZdS)z Processor class for Chameleon. ) BatchFeature) ImageInput)MultiModalDataProcessingKwargsProcessorMixin TextKwargsUnpack)PreTokenizedInput TextInput)auto_docstringceZdZUdZeed<dS)ChameleonTextKwargsa return_for_text_completion (`bool`, *optional*, defaults to `False`): Whether the processed text is intended for text completion tasks. When `True`, the processor does not append the separator token (`sep_token`) to the end of the prompt, which is typically used for chat mode. When `False`, the separator token is appended for proper chat formatting. return_for_text_completionN)__name__ __module__ __qualname____doc__bool__annotations__p/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/transformers/models/chameleon/processing_chameleon.pyrrs*!%$$$$$rrF)totalc0eZdZUeed<ddddddidZdS)ChameleonProcessorKwargs text_kwargsF)paddingrreturn_mm_token_type_idsreturn_tensorspt)r common_kwargsN)rrrrr _defaultsrrrrr*sI$$$$*/(-  d  IIIrrc eZdZeZddedeffd Zede efdZ e dd e dzd e eze e ze ezdzd eedeffd Zd ededefdZddZxZS)ChameleonProcessorimage_seq_length image_tokenct||||_t|dr|jn||_||j|_t|dr|jnd|_t|dr|j nd|_ ||j|_||j|_ ||j |_ dS)a 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. r( boi_tokenz eoi_tokenzN) super__init__r'hasattrr(convert_tokens_to_idsimage_token_idr*image_start_tokenr+image_end_tokenimage_start_token_idimage_end_token_id)selfimage_processor tokenizerr'r( __class__s rr-zChameleonProcessor.__init__<s )444 04;I}4U4Uf900[f'==d>NOO#*9k#B#B WI   7>i6U6Ucy22[c'==d>NOO$-$C$CDDZ$[$[!"+"A"A$BV"W"Wrreturnc*|j|j|jgSN)r0r3r4)r5s rimage_token_idsz"ChameleonProcessor.image_token_idsPs#T%>@WXXrNimagestextkwargsc t|tr|g}fd|D}tjd||d|}|S)aA 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`. c0g|]}|jjSr)r7 sep_token).0sampler5s r z/ChameleonProcessor.__call__..is)III&654>355IIIr)r=r>r) isinstancestrr,__call__)r5r=r>r? model_inputsr8s` rrHzChameleonProcessor.__call__Tsd" dC  6DJIIIDIII'uww'KvDKKFKK r image_inputs image_idxcD|j|j|jzz|jz}|Sr;)r1r(r'r2)r5rJrKone_img_tokenss rreplace_image_tokenz&ChameleonProcessor.replace_image_tokenms)/43CdF[3[\_c_ssrc i}|F|jdzgt|z}dgt|z}|||dtdi|S)a Computes the number of placeholder tokens needed for multimodal inputs with the given sizes. Args: image_sizes (`list[list[int]]`, *optional*): The input sizes formatted as (height, width) per each image. Returns: `MultiModalData`: A `MultiModalData` object holding number of tokens per each of the provided input modalities, along with other useful data. N)num_image_tokensnum_image_patchesr)r'lenupdater)r5 image_sizesr? vision_datarRrSs r_get_num_multimodal_tokensz-ChameleonProcessor._get_num_multimodal_tokensqst  " $ 5 9:S=M=MM !"c+&6&6 6    4D[lmm n n n,, ,,,r)r%r&)NNr;)rrrrvalid_processor_kwargsintrGr-propertylistr<r rr r r rrHdictrNrX __classcell__)r8s@rr$r$8sU5XXSX^aXXXXXX(YcYYYXY%)aeT!++d9o=EV@WWZ^^12   ^0--------rr$N)rfeature_extraction_utilsr image_utilsrprocessing_utilsrrrrr tokenization_utils_baser r utilsr rrr$__all__rrrresX544444%%%%%%DCCCCCCC######%%%%%*E%%%%     /u    M-M-M-M-M-M-M-M-` r