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.

Sign up for GitHub

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

Jump to bottom

rotary position embedding cause different output in different tensor parallel settings! #203

Open
marscrazy opened this issue Mar 16, 2023 · 1 comment
Open

rotary position embedding cause different output in different tensor parallel settings! #203

marscrazy opened this issue Mar 16, 2023 · 1 comment
Labels
model-usage issues related to how models are used/loaded

Comments

@marscrazy
Copy link

Thanks for your great work in LLM.
I have tried to load llama-13b in different mp size settings, e.g., 2,4. However, the output embedding and generated sentence changes with the change of mp settings.

My question: Is this normal?

mp size = 4
image

mp size = 2
image
@marscrazy
Copy link
Author

marscrazy commented Mar 16, 2023 •
edited
Loading

The -3.8359 is the mean of output embedding and 1.9458 is the std with mp size =4.
the mean and std is changed when mp size=2

@ejsd1989 ejsd1989 added the model-usage issues related to how models are used/loaded label Sep 6, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
model-usage issues related to how models are used/loaded
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@marscrazy @ejsd1989