Shuai Yuan

Is your implementation of Prefix tuning consistent with that of Li & Liang？

1

Acoording to your source code(https://github.com/thunlp/OpenPrompt/blob/0d7774c9bd537c96512a22ada1b3c9bf466df8f2/openprompt/prompts/prefix_tuning_template.py#L188), it seems that you only add key-value pairs for self-attention in the encoder and decoder but ignore the cross-attention in decoder. If my understanding is...