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

关于词表扩充以及垂直应用微调的问题 #16

Closed
WangRongsheng opened this issue Mar 31, 2023 · 2 comments
Closed

关于词表扩充以及垂直应用微调的问题 #16

WangRongsheng opened this issue Mar 31, 2023 · 2 comments

Comments

@WangRongsheng
Copy link

您好,我正在做一个垂直任务的微调:https://github.com/WangRongsheng/ChatGenTitle

我目前使用的是alpaca-lora 进行微调这个下游任务,我想请问:

  1. 词表扩充是只针对多语言吗?在单语言的llama模型中继续引入新的英语词表是否可以继续压榨llama模型性能?
  2. 对于我这样的垂直应用,您有什么其他的建议或者看法?

谢谢您!

@ymcui
Copy link
Owner

ymcui commented Apr 2, 2023

加入词表是有一定破坏性的, 一是破坏原有分词体系,二是增加了未训练的权重。所以如果不能进行充分训练的话,可能会有比较大的问题。个人觉得如果不是特别专的领域(比如生物医学等涉及很多专业词汇的领域)没有太大必要去扩充英文词表。

@WangRongsheng
Copy link
Author

谢谢!

yaakua pushed a commit to yaakua/Chinese-LLaMA-Alpaca that referenced this issue Apr 25, 2023
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