Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Typo in Transformer Encoder Slide 27 #18

Open
umurkarakas opened this issue Jan 8, 2025 · 0 comments
Open

Typo in Transformer Encoder Slide 27 #18

umurkarakas opened this issue Jan 8, 2025 · 0 comments

Comments

@umurkarakas
Copy link

Hello,

I believe, and as far as I remember this was also discussed in the lecture, there is a typo in slide 27/29 of Transformer Encoder lecture, where $\vec{W^{(o)}}\in \mathbb{R}^{M d_v \times d_v}$ should be $\vec{W^{(o)}}\in \mathbb{R}^{M d_v \times {d_x}}$. The example in slide 29 where $\vec{W^{(o)}}\in \mathbb{R}^{512 \times 512}$ also conforms with the corrected formula.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant