"`): 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 >X0lXplX@l[US5(a UROUUlUR URSS9SUl[T U]!XUS9 g)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 rr3LlavaProcessor.__init__Ksj%+F(.L+4;I}4U4U900[f'..t/?/?TY.Z[\] =Qrimagestextr5returnc HUcUc [S5eUR"[4SURR0UD6nUbUR "U40USD6nO0n[ U[5(aU/nO8[ U[5(d#[ US[5(d [S5eUnURS5bUSn [[U S55upXR-XR--UR-n URS:XaU S -n /nUH=n U R!UR"UR"U -5n UR%U 5 M? US R'S S5nUS R'S S 5nUR"U40US DS S0D6nUR)UUS/S9 U(aW[*R,"US5n[*R."US5nS UUUR0:H'UR35US'[50UEUEUS9$)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_liker1tolistr)r4r8r9audiovideosr5 output_kwargs image_inputsprompt_stringsr=heightwidthnum_image_tokenssampler@r text_inputs array_idsrDs r__call__LlavaProcessor.__call__]s=N >dlVW W**  "&.."<"<   //Y-:XYLL dC 6DD$'' 47C0H0H_` `   N + 7'7L*>,q/+JKMF &// 9( 00 1 22i? A% N(8(8$:J:JM]:]^%%f-'}599:JDQ#0#?#C#CD^`e#f nn^i}]7Sidhi  %%nkwi%X #[!9:I " k+.F G BC i4+>+>> ?/@/G/G/IK+ ,!@K!@r?)r^num_image_patchesr) rrrNupdater$rer,r-r.lenr ) r4 image_sizesr5 vision_datarreresized_height resized_widthr^rfs r_get_num_multimodal_tokens)LlavaProcessor._get_num_multimodal_tokenss  "0::>>PRSM   (%))+t<^@T@T@^@^I,5h,?7ASM .// AmWfWfFfg   @ @ @ 22i? A% 01C 4DD !"c+&6 6    4Dm n, ,,rc:URR"U0UD6$)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_decoder4argsr5s rrpLlavaProcessor.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%decoderqs rruLlavaProcessor.decodes ~~$$d5f55rcURRnURRn[[R X-55$N)r%model_input_namesr$rLdictfromkeys)r4tokenizer_input_namesimage_processor_input_namess rry LlavaProcessor.model_input_namess>!% @ @&*&:&:&L&L#DMM"7"UVWWr)r)r1r-r,r.)NNNNNzr)NNNNrx)rrrr__doc__ attributesimage_processor_classtokenizer_classr3rrrr rLr rrrbrmrprupropertyryr __classcell__)r6s@rr"r"-s2$[1J0%O'+$%R("^b U^U^I0$y/4HYCZZ[U^ -. U^ U^n-@<6XXrr")rtypingrnumpyrSfeature_extraction_utilsr image_utilsrrrprocessing_utilsr r r r tokenization_utils_baser rutilsr get_loggerrloggerrr"__all__rrrrsj4EE D   H %+5{X^{X|  r