Embeds the upper level music tokens and upsamples them to provide as audio conditioning.

Returns the model's output embeddings. Returns: `nn.Module`: A torch module mapping hidden states to vocabulary.

Args: tmp_dir (`string`, *optional*): if `None`: - a unique temporary path will be created

Filter dataset with heuristics. Config, test and has_no_keywords files are removed with a given probability.

Infers the channel dimension format of `image`. Args: image (`np.ndarray`): The image to infer the channel dimension of.

Cover moses empty string edge case. They return empty list for '' input!

Resizes input token embeddings matrix of the model if `new_num_tokens != config.vocab_size`. Takes care of tying weights embeddings

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

Finds the heads and their indices taking `already_pruned_heads` into account. Args: heads (`List[int]`): List of the indices of head

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

Converts an individual number passed in string form to spelt-out form

Converts `image` to the channel dimension format specified by `channel_dim`. Args: image (`numpy.ndarray`): The image to

Evaluate a python expression using the content of the variables stored in a state and only evaluating a given set of functions. This fun

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

Parse command-line args into instances of the specified dataclass types. This relies on argparse's `ArgumentParser.parse_known_args`

The index of the current process used.

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

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

Computes the output length of the convolutional layers

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

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

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

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

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

Add a new hypothesis to the list.

Returns the sequence length of the cached states. A layer index can be optionally passed.

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

Stable wrapper that returns the same output as `tf.nn.softmax`, but that works reliably with XLA on CPU. It is meant as a workaround for the

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

Alternative helper method that does not use `argparse` at all, instead loading a json file and populating the dataclass types.

Sends telemetry that helps tracking the examples use. Args: example_name (`str`): The name of the example. *example_args (da

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

To be implemented in the child class

r""" Instantiate an encoder and a decoder from one or two base classes of the library from pretrained model checkpoints. The

Convert a single image or a list of images to a list of numpy arrays. Args: images (`ImageInput`): A single image or a l

Generate the mapping between supported the features and their corresponding OnnxConfig for a given model. Args: *supported_features:

The real training loop.

From a `pretrained_model_name_or_path`, resolve to a dictionary of parameters, to be used for instantiating a [`PretrainedConfig`] us

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

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

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

Evaluate an abstract syntax tree using the content of the variables stored in a state and only evaluating a given set of functions. This

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

`tf.gather`, on which TF embedding layers are based, won't check positive out of bound indices on GPU, returning zeros instead. This function

Creates an optimizer from its config with WarmUp custom object.

Invert an attention mask (e.g., switches 0. and 1.). Args: encoder_attention_mask (`torch.Tensor`): An attention mask.

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

Will save the model, so you can reload it using `from_pretrained()`. Will only save from the main process.

projection

Temporary method to deal with `token` and `use_auth_token`. This method is to avoid apply the same changes in all model config classes that o

This function prepares a list of PIL images, or a list of numpy arrays if one specifies numpify=True, or a list of PyTorch tensors if one specifie

Register a new configuration for this class. Args: model_type (`str`): The model type like "bert" or "gpt".

Checks whether `char` is a whitespace character.

Closes the progress bar.

Activates gradient checkpointing for the current model. Note that in other frameworks this feature can be referred to as "activation