d():
        ...     for i in range(tl):
        ...         encoded = processor.tokenizer(inferred_token)
        ...         input_ids = torch.tensor(encoded.input_ids)
        ...         encoded = encoded["input_ids"][0][1:-1]
        ...         outputs = model(input_ids=input_ids, pixel_values=encoding.pixel_values)
        ...         mlm_logits = outputs.logits[0]  # shape (seq_len, vocab_size)
        ...         # only take into account text features (minus CLS and SEP token)
        ...         mlm_logits = mlm_logits[1 : input_ids.shape[1] - 1, :]
        ...         mlm_values, mlm_ids = mlm_logits.softmax(dim=-1).max(dim=-1)
        ...         # only take into account text
        ...         mlm_values[torch.tensor(encoded) != 103] = 0
        ...         select = mlm_values.argmax().item()
        ...         encoded[select] = mlm_ids[select].item()
        ...         inferred_token = [processor.decode(encoded)]

        >>> selected_token = ""
        >>> encoded = processor.tokenizer(inferred_token)
        >>> output = processor.decode(encoded.input_ids[0], skip_special_tokens=True)
        >>> print(output)
        a bunch of cats laying on a couch.
        ```N©
r“