100, 0, ...,
            config.vocab_size]` (see `input_ids` docstring) Tokens with indices set to `-100` are ignored (masked), the
            loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`

        Returns:

        Examples:

        ```python
        >>> from transformers import AutoTokenizer, PerceiverForMaskedLM
        >>> import torch

        >>> tokenizer = AutoTokenizer.from_pretrained("deepmind/language-perceiver")
        >>> model = PerceiverForMaskedLM.from_pretrained("deepmind/language-perceiver")

        >>> # training
        >>> text = "This is an incomplete sentence where some words are missing."
        >>> inputs = tokenizer(text, padding="max_length", return_tensors="pt")
        >>> # mask " missing."
        >>> inputs["input_ids"][0, 52:61] = tokenizer.mask_token_id
        >>> labels = tokenizer(text, padding="max_length", return_tensors="pt").input_ids

        >>> outputs = model(**inputs, labels=labels)
        >>> loss = outputs.loss
        >>> round(loss.item(), 2)
        19.87

        >>> logits = outputs.logits
        >>> list(logits.shape)
        [1, 2048, 262]

        >>> # inference
        >>> text = "This is an incomplete sentence where some words are missing."
        >>> encoding = tokenizer(text, padding="max_length", return_tensors="pt")

        >>> # mask bytes corresponding to " missing.". Note that the model performs much better if the masked span starts with a space.
        >>> encoding["input_ids"][0, 52:61] = tokenizer.mask_token_id

        >>> # forward pass
        >>> with torch.no_grad():
        ...     outputs = model(**encoding)
        >>> logits = outputs.logits
        >>> list(logits.shape)
        [1, 2048, 262]

        >>> masked_tokens_predictions = logits[0, 52:61].argmax(dim=-1).tolist()
        >>> tokenizer.decode(masked_tokens_predictions)
        ' missing.'
        ```Nú,You cannot use both `inputs` and `input_ids`©