[KongchangAI]
Unverified50% confidenceFactExact time

Kaplan等人2020年的Scaling Law论文揭示,在固定算力预算下,模型参数量与训练token数存在最优比例关系(Chinchilla最优)

1
Sources
50%
Confidence
Long-term
Relevance
7/16/2026
First Seen

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/530834
API
curl https://kongchang.com/api/v1/knowledge/claims/530834
MCP
get_claim(id=530834)