# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨 # This file was automatically generated from src/transformers/models/paddleocr_vl/modular_paddleocr_vl.py. # Do NOT edit this file manually as any edits will be overwritten by the generation of # the file from the modular. If any change should be done, please apply the change to the # modular_paddleocr_vl.py file directly. One of our CI enforces this. # 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨 # Copyright 2025 The PaddlePaddle Team and The HuggingFace Inc. team. All rights reserved. # # This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX # and OPT implementations in this library. It has been modified from its # original forms to accommodate minor architectural differences compared # to GPT-NeoX and OPT used by the Meta AI team that trained the model. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. import numpy as np from ...image_processing_utils import BatchFeature from ...image_utils import ImageInput from ...processing_utils import ProcessingKwargs, ProcessorMixin, Unpack from ...tokenization_utils_base import PreTokenizedInput, TextInput class PaddleOCRVLProcessorKwargs(ProcessingKwargs, total=False): _defaults = { "text_kwargs": { "padding": False, "return_mm_token_type_ids": True, }, } class PaddleOCRVLProcessor(ProcessorMixin): r""" [`PaddleOCRVLProcessor`] offers all the functionalities of [`PaddleOCRVLImageProcessor`] and [`LLamaTokenizerFast`]. See the [`~PaddleOCRVLProcessor.__call__`] and [`~PaddleOCRVLProcessor.decode`] for more information. Args: image_processor ([`PaddleOCRVLImageProcessor`], *optional*): The image processor is a required input. tokenizer ([`LLamaTokenizerFast`], *optional*): 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. """ image_processor_class = "AutoImageProcessor" tokenizer_class = "AutoTokenizer" def __init__(self, image_processor=None, tokenizer=None, chat_template=None, **kwargs): self.image_token = tokenizer.image_token self.image_token_id = tokenizer.image_token_id super().__init__(image_processor, tokenizer, chat_template=chat_template) def __call__( self, images: ImageInput = None, text: TextInput | PreTokenizedInput | list[TextInput] | list[PreTokenizedInput] = None, **kwargs: Unpack[PaddleOCRVLProcessorKwargs], ) -> BatchFeature: """ 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`. - **image_grid_thw** -- List of image 3D grid in LLM. Returned when `images` is not `None`. """ output_kwargs = self._merge_kwargs( PaddleOCRVLProcessorKwargs, tokenizer_init_kwargs=self.tokenizer.init_kwargs, **kwargs, ) if images is not None: image_inputs = self.image_processor(images=images, **output_kwargs["images_kwargs"]) image_grid_thw = image_inputs["image_grid_thw"] else: image_inputs = {} image_grid_thw = None if not isinstance(text, list): text = [text] text = text.copy() if image_grid_thw is not None: index = 0 for i in range(len(text)): while self.image_token in text[i]: text[i] = text[i].replace( self.image_token, "<|placeholder|>" * ( image_grid_thw[index].prod() // self.image_processor.merge_size // self.image_processor.merge_size ), 1, ) index += 1 text[i] = text[i].replace("<|placeholder|>", self.image_token) return_tensors = output_kwargs["text_kwargs"].pop("return_tensors", None) return_mm_token_type_ids = output_kwargs["text_kwargs"].pop("return_mm_token_type_ids", False) text_inputs = self.tokenizer(text, **output_kwargs["text_kwargs"], return_tensors=None) if return_mm_token_type_ids: array_ids = np.array(text_inputs["input_ids"]) mm_token_type_ids = np.zeros_like(text_inputs["input_ids"]) mm_token_type_ids[array_ids == self.image_token_id] = 1 text_inputs["mm_token_type_ids"] = mm_token_type_ids.tolist() return BatchFeature(data={**text_inputs, **image_inputs}, tensor_type=return_tensors) __all__ = ["PaddleOCRVLProcessor"]