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

在训练集上的后量化效果怎么样? #6

Open
xpmemeda opened this issue Nov 24, 2020 · 2 comments
Open

在训练集上的后量化效果怎么样? #6

xpmemeda opened this issue Nov 24, 2020 · 2 comments

Comments

@xpmemeda
Copy link

您好,我在复现EasyQuant的算法之后,发现确实在验证集上calibration以及easyquant可以获得更好的后量化性能。但是在训练集上来做calibration和easyquant则效果非常非常不稳定,经常eq之后的模型精度还比不上calibration。作者有做过类似的尝试吗?

@starimpact
Copy link
Collaborator

都是数据,应该不会有这样的差异,你需要仔细检查一下你的代码,或者在其它任务上尝试一下来做为对比。

@yunglechao
Copy link
Collaborator

你可以检查一下log文件,关注下量化的cos相似度在哪一层出现明显的下降,可以适当调整搜索的范围和粒度

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

3 participants