Comment by zozbot234
9 hours ago
MoE has nothing whatsoever to do with specialized task solvers. It always operates per token within a single task, you can think of it perhaps as a kind of learned "attention" for model parameters as opposed to context data.
Yes, specific weights/parameters have be trained to solve specific tasks (trained on different data).
Or did I misunderstand the concept of MoE, and it's not about having specific parts of the model (parameters) do better on specific input contexts?