"`): The special token used to indicate image in the text. image_processor tokenizer)LlamaTokenizerLlamaTokenizerFastChameleonImageProcessorimage_seq_length image_tokencX>X0l[US5(a UROUUlURUR5Ul[US5(a UR OSUl[US5(a UROSUlURUR5UlURUR 5Ul URUR5Ul URURUR/Ul [TU]5X5 g)Nr1 boi_tokenz eoi_tokenz)r0hasattrr1convert_tokens_to_idsimage_token_idr3image_start_tokenr4image_end_tokenimage_start_token_idimage_end_token_id image_idssuper__init__)selfr+r,r0r1 __class__s rr>ChameleonProcessor.__init__Ls 04;I}4U4U900[f'==d>N>NO#*9k#B#BI   7>i6U6Uy22[c'==d>N>NO$-$C$CDDZDZ$[!"+"A"A$BVBV"W--t/H/H$JaJab 4rimagestextkwargsreturnc 8[U[5(aU/nO8[U[5(d#[US[5(d [S5eUcUc [ S5eUR "[ 4SURR0UD6nUSRSS5n/nURURUR--UR-n UHOn U RURU 5n U(dXRR- n UR!U 5 MQ 0n UbUR""U40US D6n USRS S5n USRS S5n UR"U40USDS S0D6nUR%XS /S 9 U (ah[&R("US5n[&R*"US5nSU[&R,"XR.5'UR15US'[30UEU EU S9$)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_kwargsr!rF images_kwargsr$r#image) modalities input_idsmm_token_type_ids)data tensor_type) isinstancestrlist TypeError ValueError _merge_kwargsrr, init_kwargspopr8r1r0r9replace sep_tokenappendr+_check_special_mm_tokensnparray zeros_likeisinr<tolistr)r?rBrCaudiovideosrD output_kwargsrprompt_stringsone_img_tokenssample image_inputsr$r# text_inputs array_idsrMs r__call__ChameleonProcessor.__call__[sR dC 6DD$'' 47C0H0H_` ` URS-/[U5-nS/[U5-nURXES.5 [S0UD6$)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. rL)num_image_tokensnum_image_patchesr)r0lenupdater)r? image_sizesrD vision_datarnros r_get_num_multimodal_tokens-ChameleonProcessor._get_num_multimodal_tokenss_  " $ 5 5 9:S=MM !"c+&6 6    4Dm n, ,,rc:URR"U0UD6$)z This method forwards all its arguments to LlamaTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring of this method for more information. )r, batch_decoder?argsrDs rrwChameleonProcessor.batch_decodes ~~**D;F;;rc:URR"U0UD6$)z This method forwards all its arguments to LlamaTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )r,decoderxs rr|ChameleonProcessor.decodes ~~$$d5f55rcURRnURRn[[R X-55$N)r,model_input_namesr+rRdictfromkeys)r?tokenizer_input_namesimage_processor_input_namess rr$ChameleonProcessor.model_input_namess>!% @ @&*&:&:&L&L#DMM"7"UVWWr)r9r;r<r0r8r:r1r7)iz)NNNNr)rrrr__doc__ attributestokenizer_classimage_processor_classintrQr>rrrrr rRr rrrjrtrwr|propertyrr __classcell__)r@s@rr)r)5s$$[1J>O5 5S 5^a 5 5"(,hl O^$O^uY(94 ?DQbLccdeO^ 12 O^ O^b-0<6XXrr))rtypingrrnumpyr\feature_extraction_utilsr image_utilsrprocessing_utilsrr r r r tokenization_utils_baser rrrr)__all__rrrrs`#4%D%*E% /u cXcXL r