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

关于后训练量化的疑惑,真真诚诚希望得到解答 #102

Open
JoeYounger opened this issue Dec 21, 2021 · 1 comment
Open

关于后训练量化的疑惑,真真诚诚希望得到解答 #102

JoeYounger opened this issue Dec 21, 2021 · 1 comment

Comments

@JoeYounger
Copy link

您好,对您的工作表示祝贺,实在太赞了。我是名刚接触量化的萌新,最近需要实现低比特的后训练量化PTQ,由于知识有限,有两个疑问非常希望得到您的解答:
1.是只有iao才支持PTQ吗?
2.readme提到的“加载剪枝后的模型再做量化”中的量化指的是QWT还是PTQ呢?
2.我期望做低精度的PTQ(2~5bit),请问可以迁移您的工作以实现吗?还是说PTQ 只支持8bit的量化呢?
再次感谢您的工作!!!

@666DZY666
Copy link
Owner

1、是iao做PTQ效果好一些,所以只在iao里实现了PTQ;
2、都可以,但PTQ的话剪枝比例得给小一点,不然可能精度不够;
3、只是精度问题,可以直接设置bit;但保证精度的前提下,PTQ想做到4-bit以下,很难。

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

2 participants