[KongchangAI]
Unverified50% confidenceSolutionExact time

延迟解耦(Delayed Untying)的核心思想是:训练前2/3阶段将embed与lm_head绑定共享,到达某个节点后复制权重和优化器状态,然后让二者作为独立参数分别训练

1
Sources
50%
Confidence
Long-term
Relevance
8/24/2026
First Seen

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/793876
API
curl https://kongchang.com/api/v1/knowledge/claims/793876
MCP
get_claim(id=793876)