-
Notifications
You must be signed in to change notification settings - Fork 3.1k
Longlora #9970
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
Longlora #9970
Conversation
lugimzzz
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
lgtm
|
Thanks for your contribution! |
| "zero_padding": false, | ||
| "use_flash_attention": true, | ||
| "unified_checkpoint": true, | ||
| "pissa": false, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
这里的配置有问题,没有打开use_ssa,也没开use_long_strategy需要写一个能跑的配置
| @@ -0,0 +1,74 @@ | |||
| finetune: | |||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
https://github.com/PaddlePaddle/PaddleNLP/blob/develop/tests/llm/test_lora.py 参考上线需要写一个tests/llm/test_longlora.py才能执行
| import paddlenlp | ||
| from paddlenlp.transformers.llama.modeling import get_triangle_upper_mask | ||
|
|
||
| ssa_group_size_ratio = 1 / 4 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
ssa_group_size_ratio这里写死了如何通过model_args.ssa_group_size_ratio控制
PR types
New features
PR changes
Models
Description
Paddle implementation of LongLoRA