[GH-ISSUE #27] How to understand W^UK can be absorbed into W^Q and W^UV can be absorbed into W^O? #25

Closed
opened 2026-10-26 21:06:56 +00:00 by bsakaguchi · 1 comment
Owner

Originally created by @Ryuge-Kisaki on GitHub (May 13, 2024).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-V2/issues/27

Originally created by @Ryuge-Kisaki on GitHub (May 13, 2024). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-V2/issues/27
Author
Owner

@luofuli commented on GitHub (May 14, 2024):

Here's a recommended blog for you: https://spaces.ac.cn/archives/10091.
@cc752424640

<!-- gh-comment-id:2109298120 --> @luofuli commented on GitHub (May 14, 2024): Here's a recommended blog for you: https://spaces.ac.cn/archives/10091. @cc752424640
Sign in to join this conversation.
No labels
pull-request
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
deepseek-ai/DeepSeek-V2#25
No description provided.