Skip to content
RED SAGSkills
medium10 pts · first answer countsdeep-learningattentiontransformers

Where cross-attention gets keys

In an encoder-decoder transformer for translation, where do the keys and values in the decoder's cross-attention come from?

Choose one answer

Discussion 0

Join free to post in the discussion.

Related questions

More Deep learning and PyTorch questionsMore Attention questionsMore Transformers and LLM internals questions