News for hackers. Stuff that matters.
Re:Implementation of mixture of experts language model in a ... by zingelshuher on Friday March 22, 2024 @06:10PM (#39795397)
Question, have you seen the improvement after adding the noise? I mean in practice. Asking because intuition sometimes doesn't work.
Re:Implementation of mixture of experts language model in a ... by avisoori1x on Saturday March 23, 2024 @02:12PM (#39801932)
Quite honestly not in my experiments. I wanted to do some Bayesian hyperparameter optimization with some discretized options like noise/no-noise and n_expert/top_k but haven't been able to find the time or free time in one of our GPU clusters. I plan on using perplexity as this is not yet instruction fine tuned.