mlx-community/PaddleOCR-VL-4bit

1# Copyright (c) 2025 PaddlePaddle Authors. All Rights Reserved.2#3# Licensed under the Apache License, Version 2.0 (the "License");4# you may not use this file except in compliance with the License.5# You may obtain a copy of the License at6#7#     http://www.apache.org/licenses/LICENSE-2.08#9# Unless required by applicable law or agreed to in writing, software10# distributed under the License is distributed on an "AS IS" BASIS,11# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.12# See the License for the specific language governing permissions and13# limitations under the License.14 15from typing import List, Union16import numpy as np17import torch18from transformers.feature_extraction_utils import BatchFeature19from transformers.processing_utils import (20    ProcessingKwargs,21    ProcessorMixin,22    Unpack,23    VideosKwargs,24)25from transformers.tokenization_utils_base import PreTokenizedInput, TextInput26 27 28ImageInput = Union[29    "PIL.Image.Image",30    np.ndarray,31    "torch.Tensor",32    List["PIL.Image.Image"],33    List[np.ndarray],34    List["torch.Tensor"],35]  # noqa36 37 38VideoInput = Union[39    List["PIL.Image.Image"],40    "np.ndarray",41    "torch.Tensor",42    List["np.ndarray"],43    List["torch.Tensor"],44    List[List["PIL.Image.Image"]],45    List[List["np.ndarrray"]],46    List[List["torch.Tensor"]],47]  # noqa48 49 50class PaddleOCRVLVideosProcessorKwargs(VideosKwargs, total=False):51    fps: Union[List[float], float]52 53 54class PaddleOCRVLProcessorKwargs(ProcessingKwargs, total=False):55    videos_kwargs: PaddleOCRVLVideosProcessorKwargs56    _defaults = {57        "text_kwargs": {58            "padding": False,59        },60        "videos_kwargs": {"fps": 2.0},61    }62 63 64class PaddleOCRVLProcessor(ProcessorMixin):65    r"""66    [`PaddleOCRVLProcessor`] offers all the functionalities of [`SiglipImageProcessor`] and [`Qwen2TokenizerFast`]. See the67    [`~PaddleOCRVLProcessor.__call__`] and [`~PaddleOCRVLProcessor.decode`] for more information.68    Args:69        image_processor ([`SiglipImageProcessor`], *optional*):70            The image processor is a required input.71        tokenizer ([`Qwen2TokenizerFast`], *optional*):72            The tokenizer is a required input.73        chat_template (`str`, *optional*): A Jinja template which will be used to convert lists of messages74            in a chat into a tokenizable string.75    """76 77    attributes = ["image_processor", "tokenizer"]78    valid_kwargs = [79        "chat_template",80        "image_std",81        "min_pixels",82        "image_mean",83        "merge_size",84        "image_processor_type",85        "temporal_patch_size",86        "patch_size",87        "max_pixels",88    ]89 90    image_processor_class = "AutoImageProcessor"91    tokenizer_class = "AutoTokenizer"92 93    def __init__(94        self, image_processor=None, tokenizer=None, chat_template=None, **kwargs95    ):96        self.image_token = (97            "<|IMAGE_PLACEHOLDER|>"98            if not hasattr(tokenizer, "image_token")99            else tokenizer.image_token100        )101        self.video_token = (102            "<|video_pad|>"103            if not hasattr(tokenizer, "video_token")104            else tokenizer.video_token105        )106        super().__init__(image_processor, tokenizer, chat_template=chat_template)107 108    def __call__(109        self,110        images: ImageInput = None,111        text: Union[112            TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]113        ] = None,114        videos: VideoInput = None,115        **kwargs: Unpack[PaddleOCRVLProcessorKwargs],116    ) -> BatchFeature:117        """118        Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text`119        and `kwargs` arguments to Qwen2TokenizerFast's [`~Qwen2TokenizerFast.__call__`] if `text` is not `None` to encode120        the text. To prepare the vision inputs, this method forwards the `vision_infos` and `kwrags` arguments to121        SiglipImageProcessor's [`~SiglipImageProcessor.__call__`] if `vision_infos` is not `None`.122 123        Args:124            images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`):125                The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch126                tensor. Both channels-first and channels-last formats are supported.127            text (`str`, `List[str]`, `List[List[str]]`):128                The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings129                (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set130                `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).131            videos (`np.ndarray`, `torch.Tensor`, `List[np.ndarray]`, `List[torch.Tensor]`):132                The image or batch of videos to be prepared. Each video can be a 4D NumPy array or PyTorch133                tensor, or a nested list of 3D frames. Both channels-first and channels-last formats are supported.134            return_tensors (`str` or [`~utils.TensorType`], *optional*):135                If set, will return tensors of a particular framework. Acceptable values are:136                - `'tf'`: Return TensorFlow `tf.constant` objects.137                - `'pt'`: Return PyTorch `torch.Tensor` objects.138                - `'np'`: Return NumPy `np.ndarray` objects.139                - `'jax'`: Return JAX `jnp.ndarray` objects.140 141        Returns:142            [`BatchFeature`]: A [`BatchFeature`] with the following fields:143 144            - **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`.145            - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when146              `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not147              `None`).148            - **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`.149            - **pixel_values_videos** -- Pixel values of videos to be fed to a model. Returned when `videos` is not `None`.150            - **image_grid_thw** -- List of image 3D grid in LLM. Returned when `images` is not `None`.151            - **video_grid_thw** -- List of video 3D grid in LLM. Returned when `videos` is not `None`.152            - **second_per_grid_ts** -- List of video seconds per time grid. Returned when `videos` is not `None`.153        """154        output_kwargs = self._merge_kwargs(155            PaddleOCRVLProcessorKwargs,156            tokenizer_init_kwargs=self.tokenizer.init_kwargs,157            **kwargs,158        )159 160        if images is not None:161            image_inputs = self.image_processor(images=images, return_tensors="pt")162            image_inputs["pixel_values"] = image_inputs["pixel_values"]163            image_grid_thw = image_inputs["image_grid_thw"]164 165        else:166            image_inputs = {}167            image_grid_thw = None168 169        if videos is not None:170            # TODO: add video processing171            videos_inputs = self.image_processor(172                images=None, videos=videos, **output_kwargs["images_kwargs"]173            )174            video_grid_thw = videos_inputs["video_grid_thw"]175 176            fps = output_kwargs["videos_kwargs"].pop("fps", 2.0)177            if isinstance(fps, (int, float)):178                second_per_grid_ts = [179                    self.image_processor.temporal_patch_size / fps180                ] * len(video_grid_thw)181            elif hasattr(fps, "__len__") and len(fps) == len(video_grid_thw):182                second_per_grid_ts = [183                    self.image_processor.temporal_patch_size / tmp for tmp in fps184                ]185            else:186                raise ValueError(187                    f"The length of fps ({len(fps) if hasattr(fps, '__len__') else fps}) must be equal to the length of video_grid_thw ({len(video_grid_thw)}) or fps should be a single number."188                )189            videos_inputs.update(190                {"second_per_grid_ts": torch.tensor(second_per_grid_ts)}191            )192 193        else:194            videos_inputs = {}195            video_grid_thw = None196 197        if not isinstance(text, list):198            text = [text]199 200        if image_grid_thw is not None:201            index = 0202            for i in range(len(text)):203                while self.image_token in text[i]:204                    text[i] = text[i].replace(205                        self.image_token,206                        "<|placeholder|>"207                        * (208                            image_grid_thw[index].prod()209                            // self.image_processor.merge_size210                            // self.image_processor.merge_size211                        ),212                        1,213                    )214                    index += 1215                text[i] = text[i].replace("<|placeholder|>", self.image_token)216 217        if video_grid_thw is not None:218            index = 0219            for i in range(len(text)):220                while self.video_token in text[i]:221                    text[i] = text[i].replace(222                        self.video_token,223                        "<|placeholder|>"224                        * (225                            video_grid_thw[index].prod()226                            // self.image_processor.merge_size227                            // self.image_processor.merge_size228                        ),229                        1,230                    )231                    index += 1232                text[i] = text[i].replace("<|placeholder|>", self.video_token)233 234        text_inputs = self.tokenizer(text, **output_kwargs["text_kwargs"])235 236        return BatchFeature(data={**text_inputs, **image_inputs, **videos_inputs})237 238    def batch_decode(self, *args, **kwargs):239        """240        This method forwards all its arguments to Qwen2TokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please241        refer to the docstring of this method for more information.242        """243        return self.tokenizer.batch_decode(*args, **kwargs)244 245    def decode(self, *args, **kwargs):246        """247        This method forwards all its arguments to Qwen2TokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to248        the docstring of this method for more information.249        """250        return self.tokenizer.decode(*args, **kwargs)251 252    def post_process_image_text_to_text(253        self,254        generated_outputs,255        skip_special_tokens=True,256        clean_up_tokenization_spaces=False,257        **kwargs,258    ):259        """260        Post-process the output of the model to decode the text.261 262        Args:263            generated_outputs (`torch.Tensor` or `np.ndarray`):264                The output of the model `generate` function. The output is expected to be a tensor of shape `(batch_size, sequence_length)`265                or `(sequence_length,)`.266            skip_special_tokens (`bool`, *optional*, defaults to `True`):267                Whether or not to remove special tokens in the output. Argument passed to the tokenizer's `batch_decode` method.268            Clean_up_tokenization_spaces (`bool`, *optional*, defaults to `False`):269                Whether or not to clean up the tokenization spaces. Argument passed to the tokenizer's `batch_decode` method.270            **kwargs:271                Additional arguments to be passed to the tokenizer's `batch_decode method`.272 273        Returns:274            `List[str]`: The decoded text.275        """276        return self.tokenizer.batch_decode(277            generated_outputs,278            skip_special_tokens=skip_special_tokens,279            clean_up_tokenization_spaces=clean_up_tokenization_spaces,280            **kwargs,281        )282 283    @property284    def model_input_names(self):285        tokenizer_input_names = self.tokenizer.model_input_names286        image_processor_input_names = self.image_processor.model_input_names287        names_from_processor = list(288            dict.fromkeys(tokenizer_input_names + image_processor_input_names)289        )290        return names_from_processor + ["second_per_grid_ts"]291 292 293__all__ = ["PaddleOCRVLProcessor", "PaddleOCRVLProcessor"]294