Initialize and prunes weights if needed.

Loads a vocabulary file into a dictionary.

Cross Entropy in the language case Args: x: (batch_size, seq_len) z: (batch_size, n_sample, nz) Returns:

Prepare the dataloader from config.

Prepare the model from config.

Prunes heads of the base model. Arguments: heads_to_prune: dict with keys being selected layer indices (`int`) and asso

Restore the parameters stored with the `store` method. Useful to validate the model with EMA parameters without affecting the

Check ETag on S3 object.

Pull a file directly from S3.

Save the tokenizer vocabulary to a directory. This method does *NOT* save added tokens and special token mappings. Please us

Save the current parameters for restoring later. Args: parameters: Iterable of `torch.nn.Parameter`; the parameters to be

Make sure we are sharing the input and output embeddings. Export to TorchScript can't handle parameter sharing so we are cloning them ins

Make sure we are sharing the input and output embeddings. Export to TorchScript can't handle parameter sharing so we are cloning them ins

Make sure we are sharing the input and output embeddings. Export to TorchScript can't handle parameter sharing so we are cloning them ins

Make sure we are sharing the input and output embeddings. Export to TorchScript can't handle parameter sharing so we are cloning them ins

Serializes this instance to a Python dictionary.

Save this instance to a json file.

Filter a distribution of logits using top-k and/or nucleus (top-p) filtering Args: logits: logits distribution shape (vocabulary

Convert `url` into a hashed filename in a repeatable way. If `etag` is specified, append its hash to the url's, delimited by a period.

Construct model based on the config.