New ask Hacker News story: Ask HN: Transformer alternatives that could have emergent properties when scaled
Ask HN: Transformer alternatives that could have emergent properties when scaled
3 by s_r_n | 1 comments on Hacker News.
I am trying to identify model architecture candidates that could, like transformers, have "emergent" properties when they are scaled (see https://ift.tt/qFr8D16). Some contenders I already know about are: * Monarch Mixer (https://ift.tt/WJ8atEp) * Hyena (https://ift.tt/nDjKVp5) Thanks for your help.
3 by s_r_n | 1 comments on Hacker News.
I am trying to identify model architecture candidates that could, like transformers, have "emergent" properties when they are scaled (see https://ift.tt/qFr8D16). Some contenders I already know about are: * Monarch Mixer (https://ift.tt/WJ8atEp) * Hyena (https://ift.tt/nDjKVp5) Thanks for your help.
Comments
Post a Comment