# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨 # This file was automatically generated from src/transformers/models/deepseek_vl/modular_deepseek_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_deepseek_vl.py file directly. One of our CI enforces this. # 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨 # Copyright 2025 Deepseek AI and The HuggingFace Team. All rights reserved. # # 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. from typing import Union from ...image_processing_utils import BatchFeature from ...image_utils import ImageInput, make_flat_list_of_images from ...processing_utils import ProcessingKwargs, ProcessorMixin, Unpack from ...tokenization_utils_base import PreTokenizedInput, TextInput class DeepseekVLProcessorKwargs(ProcessingKwargs, total=False): _defaults = { "text_kwargs": {"padding": False}, "common_kwargs": {"return_tensors": "pt"}, } class DeepseekVLProcessor(ProcessorMixin): r""" Constructs a DeepseekVL processor which wraps a DeepseekVL Image Processor and a Llama tokenizer into a single processor. [`DeepseekVLProcessor`] offers all the functionalities of [`DeepseekVLImageProcessor`] and [`LlamaTokenizerFast`]. See the [`~DeepseekVLProcessor.__call__`] and [`~DeepseekVLProcessor.decode`] for more information. Args: image_processor ([`DeepseekVLImageProcessor`]): The image processor is a required input. tokenizer ([`LlamaTokenizerFast`]): 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. num_image_tokens (`int`, *optional*, defaults to 576): The number of special image tokens used as placeholders for visual content in text sequences. """ attributes = ["image_processor", "tokenizer"] valid_kwargs = ["chat_template", "num_image_tokens"] image_processor_class = "AutoImageProcessor" tokenizer_class = "AutoTokenizer" def __init__( self, image_processor, tokenizer, chat_template=None, num_image_tokens=576, ): self.image_token = tokenizer.image_token self.num_image_tokens = num_image_tokens super().__init__(image_processor, tokenizer, chat_template=chat_template) def __call__( self, text: Union[TextInput, PreTokenizedInput, list[TextInput], list[PreTokenizedInput]] = None, images: ImageInput = None, **kwargs: Unpack[DeepseekVLProcessorKwargs], ) -> BatchFeature: """ 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 DeepseekVLImageProcessor's [`~DeepseekVLImageProcessor.__call__`] if `images` is not `None`. Please refer to the doctsring of the above two methods for more information. Args: 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). 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. 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`. """ output_kwargs = self._merge_kwargs( DeepseekVLProcessorKwargs, tokenizer_init_kwargs=self.tokenizer.init_kwargs, **kwargs ) if text is None and images is None: raise ValueError("You must specify either text or images.") if text is not None: if isinstance(text, str): text = [text] elif not (isinstance(text, (list, tuple)) and all(isinstance(t, str) for t in text)): raise ValueError("Invalid input text. Please provide a string, or a list of strings") prompt_strings = [] one_img_tokens = self.image_token * self.num_image_tokens for prompt in text: prompt = prompt.replace(self.image_token, one_img_tokens) prompt_strings.append(prompt) data = self.tokenizer(prompt_strings, **output_kwargs["text_kwargs"]) # process images if pixel_values are provided if images is not None: images = make_flat_list_of_images(images) data["pixel_values"] = self.image_processor(images, **output_kwargs["images_kwargs"])["pixel_values"] return BatchFeature(data=data) def batch_decode(self, *args, **kwargs): """ This method forwards all its arguments to LlamaTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring of this method for more information. """ return self.tokenizer.batch_decode(*args, **kwargs) def decode(self, *args, **kwargs): """ This method forwards all its arguments to LlamaTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. """ return self.tokenizer.decode(*args, **kwargs) @property def model_input_names(self): tokenizer_input_names = self.tokenizer.model_input_names image_processor_input_names = self.image_processor.model_input_names return list(dict.fromkeys(tokenizer_input_names + image_processor_input_names)) __all__ = ["DeepseekVLProcessor"]