Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
Apache License 2.0
2.41k
stars
248
forks
source link
dimensions of encoder_attention_mask in inputs of OFADecoder #384
This annotation may be wrong:
encoder_attention_mask (torch.Tensorof shape(bsz, seq_len)): the padding mask of the source side.
Does it refer to:
shape (bsz, 1, tgt_len, src_len)
This annotation may be wrong:
encoder_attention_mask (
torch.Tensorof shape
(bsz, seq_len)): the padding mask of the source side.
Does it refer to:shape (bsz, 1, tgt_len, src_len)