Press Space to continue
ByteDance's development of a 10 trillion parameter model
Press Space to continue
There was news reports yesterday that ByteDance was considering training a 5T model. That story escalated during the night, and the FT is now reporting that ByteDance are currently pre-training a 10T that should be ready before the end of the year.
open on x · 1 viewViews and clicks count once per visitor per day. Clicks are opens of this post on X.