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

使用demo中训练后的Lora模型,结果出现大量重复 #2

Open
nilin1998 opened this issue May 31, 2023 · 3 comments
Open

使用demo中训练后的Lora模型,结果出现大量重复 #2

nilin1998 opened this issue May 31, 2023 · 3 comments

Comments

@nilin1998
Copy link

加载项目中的output/adgen-chatglm-6b-lora模型,运行cli_demo.py,结果中出现了大量重复语句,如图:
image

@zejunwang1
Copy link
Owner

加载项目中的output/adgen-chatglm-6b-lora模型,运行cli_demo.py,结果中出现了大量重复语句,如图: image

偶尔是会有重复的生成,你多输入几次试试

@nilin1998
Copy link
Author

还有一个问题,采用lora这种训练方式,理论上不会出现灾难性遗忘的现象,但是加载你给的训练模型,输入hello,输出是乱码

@zejunwang1
Copy link
Owner

还有一个问题,采用lora这种训练方式,理论上不会出现灾难性遗忘的现象,但是加载你给的训练模型,输入hello,输出是乱码

理论和实际可能是不一样的,lora 是额外训练了一个旁路的矩阵参数,你加载 lora 训练后的 checkpoint,模型输出可能是会受到微调数据集和训练参数的影响。

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