We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? # to your account
Hi, In this line:
Transformer/Embed.py
Line 12 in 37bf492
I think you need to multiply the embedding by sqrt(d_model)
The text was updated successfully, but these errors were encountered:
@orena1 Hi, the implementation also didn't share the embedding weights, right?
Sorry, something went wrong.
@orena1 The code actually has * math.sqrt(self.d_model) in the positional embedding class. In forward method.
Did somebody know the reason for multiplying embedding weights by sqrt(d_model)?
Yes, the implementation didn't share the embedding weights.
No branches or pull requests
Hi,
In this line:
Transformer/Embed.py
Line 12 in 37bf492
I think you need to multiply the embedding by sqrt(d_model)
The text was updated successfully, but these errors were encountered: