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

The upper and lower bounds seems to not 8 bits in some cases #96

Open
zhangyu68 opened this issue Oct 30, 2024 · 0 comments
Open

The upper and lower bounds seems to not 8 bits in some cases #96

zhangyu68 opened this issue Oct 30, 2024 · 0 comments

Comments

@zhangyu68
Copy link

zhangyu68 commented Oct 30, 2024 •
edited
Loading

I noticed that the rounding method uses round(), this results in values ​​ranging from -128 to 128, rather than -128 to 127. So maybe is not a 8bit quant in some cases, at least I found this problem on llama3. I guess this has something to do with the distribution of parameters.
Can you give me some advice?

image
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@zhangyu68