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

关于数据集处理 #37

Open
kostya-sec opened this issue May 28, 2023 · 4 comments
Open

关于数据集处理 #37

kostya-sec opened this issue May 28, 2023 · 4 comments
Labels
question Further information is requested wontfix This will not be worked on

Comments

@kostya-sec
Copy link

Describe the Question

Please provide a clear and concise description of what the question is.

Describe your attempts

  • [ x] I walked through the tutorials
  • [x ] I checked the documentation
  • [ x] I checked to make sure that this is not a duplicate question

您好。我想尝试微调关于剧本的llama 使用的Lora。我看到指令精调使用数据模板是
{
"instruction": "",
"input": "",
"output": ""
}
我的原始数据类似下面这种:
一些环境描述和背景描述。
旁白:旁白说的话1.
角色1:角色1的话1. (角色情绪和动作)
角色2:角色2的话1. (角色情绪和动作)
xxxx

如果是这样的话,想请教一下应该怎么样处理源数据到模板数据会比较合适。非常感谢

@kostya-sec kostya-sec added the question Further information is requested label May 28, 2023
@shibing624
Copy link
Owner

多轮对话数据集和角色扮演数据,我稍后给个示例,一般来说是把人物加对白拼接起来当做上下文处理。

@kostya-sec
Copy link
Author

多轮对话数据集和角色扮演数据,我稍后给个示例,一般来说是把人物加对白拼接起来当做上下文处理。

非常感谢

@Godlikemandyy
Copy link

多轮对话数据集和角色扮演数据,我稍后给个示例,一般来说是把人物加对白拼接起来当做上下文处理。

期待来个多轮对话的示例数据,顺便问一下大佬,lora多轮对话微调效果如何?想做一下lora的多轮对话微调

Copy link

stale bot commented Dec 27, 2023

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.(由于长期不活动,机器人自动关闭此问题,如果需要欢迎提问)

@stale stale bot added the wontfix This will not be worked on label Dec 27, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested wontfix This will not be worked on
Projects
None yet
Development

No branches or pull requests

3 participants