Function _prepare_bart_decoder_inputs

src/transformers/modeling_bart.py:115–133

Prepare masks that ignore padding tokens in the decoder and a causal mask for the decoder if none are provided. This mimics the default behavior in fairseq. To override it pass in masks. Note: this is not called during generation

(
    config, input_ids, decoder_input_ids=None, decoder_padding_mask=None, causal_mask_dtype=torch.float32
)

def _prepare_bart_decoder_inputs(
    config, input_ids, decoder_input_ids=None, decoder_padding_mask=None, causal_mask_dtype=torch.float32
):
    """Prepare masks that ignore padding tokens in the decoder and a causal mask for the decoder if
    none are provided. This mimics the default behavior in fairseq. To override it pass in masks.
    Note: this is not called during generation
    """
    pad_token_id = config.pad_token_id
    if decoder_input_ids is None:
        decoder_input_ids = shift_tokens_right(input_ids, pad_token_id)
    bsz, tgt_len = decoder_input_ids.size()
    if decoder_padding_mask is None:
        decoder_padding_mask = make_padding_mask(decoder_input_ids, pad_token_id)
    else:
        decoder_padding_mask = invert_mask(decoder_padding_mask)
    causal_mask = torch.triu(fill_with_neg_inf(torch.zeros(tgt_len, tgt_len)), 1).to(
        dtype=causal_mask_dtype, device=decoder_input_ids.device
    )
    return decoder_input_ids, decoder_padding_mask, causal_mask


class PretrainedBartModel(PreTrainedModel):