Parameters
概念
核心技术
The learned numbers — and why 'bigger' stopped being the whole story.
您正在查看一条概念解释记录：该术语的通俗含义，以及它所关联的各条目。
Parameters are the weights a model learns; storing and moving them is what all the memory on this site is for (a 405B-parameter model needs ~800 GB at 16-bit). Counts climbed from GPT-2's 1.5B to trillion-parameter mixtures, but since Chinchilla the field optimizes parameters against data and compute jointly — and closed labs stopped disclosing counts at all, which is why so many records here say 'not publicly disclosed.'
它如何与整个技术栈相连
本记录的关联链接一览——点击分组可直接跳转。
来源
记录审阅截至 2026-01-15 — 查看 方法论.