Attn Mask for Non-causal Models

[roshansh-cmu]

We are examining non-NLP applications of the cosformer self-attention, and would need to use attention masking for the padded tokens in the batch. Is there a way to incorporate this ? Because the code does not explicitly compute the attention weights on which masking is traditionally applied.

[Doraemonzzz]

We are examining non-NLP applications of the cosformer self-attention, and would need to use attention masking for the padded tokens in the batch. Is there a way to incorporate this ? Because the code does not explicitly compute the attention weights on which masking is traditionally applied.

Can you provide some examples before/after masking?

[npzl]

for example, Swin-transformer mask