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

请问如果想将模型参数量从0.1B改为0.2B,或者改为0.05B,应该改动哪些参数呢? #12

Closed
ybdesire opened this issue Nov 18, 2024 · 4 comments

Comments

@ybdesire
Copy link

No description provided.

@ybdesire
Copy link
Author

请问是改这个config.json就可以吗?
https://github.com/AI-Study-Han/Zero-Chatgpt/blob/main/pretrain/model/config.json
大概要改哪些参数呢?

@AI-Study-Han
Copy link
Owner

是的,可以修改层数和每层的尺寸

@ybdesire
Copy link
Author

是的,可以修改层数和每层的尺寸

谢谢您的回复。再请教一下,如果把 "num_hidden_layers": 24 改为 "num_hidden_layers": 12 ,模型总参数量就变为 0.05B 了是吗?

@AI-Study-Han
Copy link
Owner

是的,可以修改层数和每层的尺寸

谢谢您的回复。再请教一下,如果把 "num_hidden_layers": 24 改为 "num_hidden_layers": 12 ,模型总参数量就变为 0.05B 了是吗?

不是,因为模型较小的话,embedding 参数占比较大,只修改层数这部分参数没有变化,并不是单纯的1/2的关系,这个你可以计算一下。

@ybdesire ybdesire closed this as completed Dec 8, 2024
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