r""" Instantiate a [`EncoderDecoderConfig`] (or a derived class) from a pre-trained encoder model configuration and decoder model conf

Whether or not this process is the global main process (when training in a distributed fashion on several machines, this is only goin

r""" Generates sequences for models with a language modeling head using multinomial sampling. Parameters: input_ids (`tf.

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

Creates a draft of a model card using the information available to the `Trainer`. Args: language (`str`, *optional*):

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

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

Calculates a spectrogram over one waveform using the Short-Time Fourier Transform. This function can create the following kinds of spectrogr

Temporarily updates the `os.environ` dictionary in-place. Similar to mockenv The `os.environ` dictionary is updated in-place so that the mod

Very simple data collator that simply collates batches of dict-like objects and performs special handling for potential keys named:

Encodes the input audio waveform into discrete codes. Args: input_values (`torch.Tensor` of shape `(batch_size, channels

CrossEntropyLoss that ignores pad tokens

Function that is called by `.generate()` to push new tokens

Converts an index (integer) in a token (str) using the vocab.

Detects whether the optional user-specified attention_mask & the automatically created causal mask can be ignored in case PyTorch's SDPA is u

start tracking for the caller's stage

Get the index of the token in the encoded output comprising a character in the original string for a sequence of the batch.

Args: dimension: fixed_dimension: num_token_to_add: Returns:

r""" Instantiate a [`CLIPConfig`] (or a derived class) from clip text model configuration and clip vision model configuration.

Get the `out_features` and `out_indices` so that they are aligned. The logic is as follows: - `out_features` not set, `out_indices`

Temporarily patches the variables defines in `tests_fetcher` to use a different location for the repo.

Util for integration test. Text is tokenized and then reverted back to text. Both results are then checked. Args:

Checks whether `chars` is a punctuation character.

Generate an image from the given prompts. If image_path is provided, the image is used as a starting point for the optimization. If im

Loads the backbone model from a config object. If the config is from the backbone model itself, then we return a backbone model with randoml

Creates a frequency bin conversion matrix used to obtain a mel spectrogram. This is called a *mel filter bank*, and various implementation ex