Add a list of new tokens to the tokenizer class. If the new tokens are not in the vocabulary, they are added to it with indices start

Send all values to device by calling `v.to(*args, **kwargs)` (PyTorch only). This should support casting in different `dtypes` and se

Ensure that the output is a flat list of images. If the input is a single image, it is converted to a list of length 1. If the input is a nes

r""" quantized_representation (torch.Tensor of shape `(batch_size, dimension, time_steps)`, *optional*): Quantized continuous repr

Add a dictionary of special tokens (eos, pad, cls, etc.) to the encoder and link them to class attributes. If special tokens are NOT

Tie or clone module weights depending of whether we are using TorchScript or not

Map inputs to attention experts according to routing decision and compute query projection inside each experts.

Returns the text config related to the text input (encoder) or text output (decoder) of the model. The `decoder` and `encoder` input

Convert self to a tuple containing all the attributes/keys that are not `None`.

Casts an input to a torch int64 tensor if we are in a tracing context, otherwise to a Python int.

Checks validity of typically used arguments in an `ImageProcessor` `preprocess` method. Raises `ValueError` if arguments incompatibility is c

Checks to see whether the pixel values have already been rescaled to [0, 1].

Converts bounding boxes from center format to corners format. center format: contains the coordinate for the center of the box and its width

This function prepares a list of PIL images

Validate the RoPE config arguments, given a `PreTrainedConfig` object

Basic Tokenization of a piece of text. For sub-word tokenization, see WordPieceTokenizer. Args: never_split (`List[str]`

Method to merge dictionaries of kwargs cleanly separated by modality within a Processor instance. The order of operations is as follo

Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens

Returns the number of added tokens when encoding a sequence with special tokens. <Tip> This encodes a dummy input and check

Creates a non-causal 4D mask of shape `(batch_size, 1, query_length, key_value_length)` from a 2D mask of shape `(batch_size, key_value_lengt

Updates the padding cache with the new padding states for the layer `layer_idx` and returns the current cache. Parameters:

Create a standard bidirectional mask based on the attention implementation used (stored in the config). Args: config (`PreTrainedCon

A context manager for torch distributed environment where on needs to do something on the main process, while blocking replicas, and

Rescale and normalize images. Override to rescale and normalize the images in torch.bfloat16 as in the original implementation

Shows a one-time warning if the input_ids appear to contain padding and no attention mask was given.

`torch.device`: The device on which the module is (assuming that all the module parameters are on the same device).

Tries to locate a file in a local folder and repo, downloads and cache it if necessary. Args: path_or_repo_id (`str` or `os.PathLike

Args: append_path: optional path to append to the tests dir path Return: The full path to the `tests` dir, so that the tests

Upload `self.model` and `self.processing_class` to the 🤗 model hub on the repo `self.args.hub_model_id`. Parameters: com

Computes the output length of the convolutional layers

Helper function for reproducible behavior to set the seed in `random`, `numpy`, `torch` (if installed). Args: seed (`int`):

Loads `image` to a PIL Image. Args: image (`str` or `PIL.Image.Image`): The image to convert to the PIL Image format.

Performs a single optimization step Arguments: closure (callable, optional): A closure that reevaluates the model

Run evaluation and returns metrics. The calling script will be responsible for providing a method to compute metrics, as they are ta

Clears the console.

Run pipeline tests for a specific `task` Args: task (`str`): A task name. This should be a key in the mapping `pi

Rescale the image by the given factor. image = image * rescale_factor. Args: image (`np.ndarray`): Image

A context manager under which models are initialized with all parameters on the meta device, therefore creating an empty model. Useful when j

Checks whether `char` is a whitespace character.

Constructs a `ModelCard` from a json file of parameters.

Defaulting to audio config as it's the decoder in this case which is usually the text backbone

Activates gradient checkpointing for the current model. We pass the `__call__` method of the modules instead of `forward` because `_

Check if `torch_xla` is available. To train a native pytorch job in an environment with torch xla installed, set the USE_TORCH_XLA to false.

Applies the transformation to a coordinate tensor. Args: pts: A [*, 3] coordinate tensor. Returns: T

Convert a single or a list of urls into the corresponding `PIL.Image` objects. If a single url is passed, the return value will be a

Returns an array containing the specified window. This window is intended to be used with `stft`. The following window types are supported:

Args: Converts a string to a sequence of ids (integer), using the tokenizer and vocabulary. Same as doing `self.convert_token

Tests if `x` is a torch tensor or not. Safe to call even if torch is not installed.

Center crop an image to a certain size. Args: image (`np.ndarray`): Image to center crop. cr

Tokenize and prepare for the model a sequence or a pair of sequences. <Tip warning={true}> This method is deprecated, `__ca

Perform a runtime check of the dependency versions, using the exact same syntax used by pip. The installed module version comes from the *si

Checks whether `char` is a punctuation character.