adapt for transformers processing

processing_minicpmv.py

@@ -53,62 +53,13 @@ class MiniCPMVProcessor(ProcessorMixin):
         text: Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]],
         images: ImageInput = None,
         padding: Union[bool, str, PaddingStrategy] = False,
-        truncation: Union[bool, str, TruncationStrategy] = None,
         max_length: Optional[int] = None,
         do_pad: Optional[bool] = True,
         return_tensors: Optional[Union[str, TensorType]] = TensorType.PYTORCH,
     ) -> MiniCPMVBatchFeature:
-        """
-        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
-        LlavaNextImageProcessor's [`~LlavaNextImageProcessor.__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.
-            padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `False`):
-                Select a strategy to pad the returned sequences (according to the model's padding side and padding
-                index) among:
-                - `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single
-                  sequence if provided).
-                - `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum
-                  acceptable input length for the model if that argument is not provided.
-                - `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different
-                  lengths).
-            max_length (`int`, *optional*):
-                Maximum length of the returned list and optionally padding length (see above).
-            do_pad (`bool`, *optional*, defaults to self.do_pad):
-                Whether to pad the image. If `True` will pad the images in the batch to the largest image in the batch
-                and create a pixel mask. Padding will be applied to the bottom and right of the image with zeros.
-            truncation (`bool`, *optional*):
-                Activates truncation to cut input sequences longer than `max_length` to `max_length`.
-            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`.
-        """
         if images is not None:
             image_inputs = self.image_processor(images, do_pad=do_pad, return_tensors=return_tensors)
-        return self._convert_images_texts_to_inputs(image_inputs, text, max_length=max_length)
+        return self._convert_images_texts_to_inputs(image_inputs, text, max_length=max_length, return_tensors=return_tensors)
     
     # Copied from transformers.models.clip.processing_clip.CLIPProcessor.batch_decode with CLIP->Llama
     def batch_decode(self, *args, **kwargs):
@@ -185,7 +136,7 @@ class MiniCPMVProcessor(ProcessorMixin):
             "pixel_values": images,
             "image_sizes": [image_sizes],
             "image_bounds": [image_bounds]
-        })
+        }, tensor_type=return_tensors)
 
     @property
     # Copied from transformers.models.clip.processing_clip.CLIPProcessor.model_input_names