Re:Transformer Attention is off by one
by WithinReason on Monday July 24, 2023 @04:41PM
(#36853908)
* * *
Sure, emergent properties can arise as parameters increase. Everyone knows that. That’s a much less specific claim than to say that the benefit of modifying softmax can only arise as an emergent property after N parameters, and therefore the benefit can only be evaluated on models above a certain size. To my understanding the author of TFA isn’t suggesting the same issue as the one in your linked paper.
Re:Transformer Attention is off by one
by WithinReason on Monday July 24, 2023 @06:08PM
(#36854931)
The second heading in the TFA is "It’s All About Outliers"
Re:Transformer Attention is off by one
by PoignardAzur on Monday July 24, 2023 @06:18PM
(#36855021)
6.7B isn't "needs a datacenter" scale.
Re:Transformer Attention is off by one
by WithinReason on Monday July 24, 2023 @06:28PM
(#36855130)
It's in the million dollar range. XLnet which is a 1.3B model cost $245,000 to train for example.
Any reason to believe this? The author never mentioned it, and I can’t think of any other a priori reason why it should be true.