From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :)
Why do you think that https://github.com/leapingio/leaping is a good alternative to makeMoE
From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :)
Why do you think that https://github.com/leapingio/leaping is a good alternative to makeMoE