-
Notifications
You must be signed in to change notification settings - Fork 18
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Lora秩的变化 #8
Comments
应该的确是一种简化的方案,感谢你的提议! |
感觉理论上,concat和add是等价的,因为add后的那些矩阵本质上也是∑AB,做正交loss的话计算方式上是一样的,就是forward感觉可能不太一样了。concat的话rank会增长,add的话rank不会增长? |
个人理解哈,欢迎拍砖。 |
大佬有试过在训练阶段使用concat和add两种方式最终效果的对比吗 |
我在文字领域没有尝试,但是在CV领域尝试了,把作者代码迁移到自己的感知工程里。 |
感谢大佬的回复,我再理解一下:
我的理解对吗? |
这里的add,像你之前提到的∑AB,就是这样子。 |
感谢您的工作,非常的nice!但还是有几个问题想请教一下:
我还没成功run起代码来,hf被墙很烦,所以这些问题还暂时没有亲手验证,烦请作者帮忙解惑一下啦~
The text was updated successfully, but these errors were encountered: