Hi, I have questions about the Rag model.
In this paper, the query encoder is DPR and the generator is Bart.
My questions are:
- Is the generator a full Bart or just the decoder part of the Bart.
- If I implement a Rag with the encoder part of Bart as the query encoder, and decoder part of the Bart as generator. Does that make sense w.r.t the Rag concept? I think this is more intuitive to me. why they use a ‘heterogeneous’ setting?