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

模型结构错误 #3

Open
mobius10 opened this issue Mar 15, 2025 · 5 comments
Open

模型结构错误 #3

mobius10 opened this issue Mar 15, 2025 · 5 comments

Comments

@mobius10
Copy link

mobius10 commented Mar 15, 2025 •
edited
Loading

由于huggingface模型的访问限制，我使用--model_name_or_path "huggyllama/llama-7b" 命令提供模型。我按页面上的方法执行bash scripts/train_fb.sh TransE时，报错如下：
Image
见倒数第二行，提示矩阵尺寸不匹配。请问如何解决？
@NJULY
Copy link
Collaborator

NJULY commented Mar 15, 2025

多贴一点报错信息，现在看不到是哪一段代码触发的这个错误

@mobius10
Copy link
Author

多贴一点报错信息，现在看不到是哪一段代码触发的这个错误
dift虚拟环境和你要求的一模一样，除了bitsandbytes==0.45.3，我的CUDA是12.4，按你的版本会报CUDA不兼容错误。上次错误更具体的报错如下图。期待您的回复。
Image

@NJULY
Copy link
Collaborator

NJULY commented Mar 16, 2025

TransE的embedding维度是多少，我用的是100，如果你自己训练了TransE的话，要把train.py第39行修改一下

@mobius10
Copy link
Author

TransE的embedding维度是多少，我用的是100，如果你自己训练了TransE的话，要把train.py第39行修改一下

我是直接下载您的dataset数据集跑的。

@NJULY
Copy link
Collaborator

NJULY commented Mar 16, 2025

抱歉，这个是我记错了，TransE的embedding维度是250。我更新了一下train.py和eval.py，把TransE embedding_dim手动设置为了250

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
2 participants
@NJULY @mobius10