You Could Have Come Up with Kimi Delta Attention

> 你本可以自己想出Kimi Delta Attention

HN 186 分 · 62 条评论 · 作者 AnhTho_FR · 来源 blog.doubleword.ai · HN 讨论

> HN 186分 · 62条评论 · 作者 AnhTho_FR · 来源 blog.doubleword.ai · HN讨论

The article uses bra-ket notation to explain the derivation of linear attention variants, specifically tracing the evolution from standard attention to DeltaNet and Kimi Delta Attention.

⋯ 继续阅读请开通会员 ⋯