openai/CLIP
1
0
Fork 0
mirror of https://github.com/openai/CLIP.git synced 2026-11-05 01:37:26 +00:00
Code Issues 274 Projects Packages Wiki Activity

[GH-ISSUE #104] ViT self-attention has no Q,K,V weights #96

New issue
Closed
opened 2026-10-31 21:11:03 +00:00 by bsakaguchi · 0 comments
bsakaguchi commented 2026-10-31 21:11:03 +00:00
Owner
Copy link

Originally created by @drjinying on GitHub (May 7, 2021).
Original GitHub issue: https://github.com/openai/CLIP/issues/104

Just to make sure, is it intended that the ViT's MultiHeadAttention layer has no Q, K and V matrixes?
In the code, x value is used for q, k and v. The paper didn't mention this. Could you please share any insights?

I figured this out. The nn.MultiheadAttention built wq, wk, wv inside. Thanks!

Originally created by @drjinying on GitHub (May 7, 2021). Original GitHub issue: https://github.com/openai/CLIP/issues/104 Just to make sure, is it intended that the ViT's MultiHeadAttention layer has no Q, K and V matrixes? In the code, x value is used for q, k and v. The paper didn't mention this. Could you please share any insights? --- I figured this out. The nn.MultiheadAttention built wq, wk, wv inside. Thanks!
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
codex/pin-github-workflow-refs-20260325-132838
jongwook/issue-396
jongwook-patch-1
No results found.
Labels
Clear labels   
pull-request
Mirrored from GitHub Pull Request

No labels
pull-request
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
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
openai/CLIP#96
No description provided.