-
Notifications
You must be signed in to change notification settings - Fork 1.6k
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
微调代码什么时候能够发布 #2
Comments
+1 |
+1支持 |
+1 |
推荐一手我们团队开发的微调工具库:XTuner 一键启动ChatGLM3-6B-Base, QLoRA, open assistant 数据集(显存占用 11GB 左右)
|
chatGLM2的微调代码适用不?很好奇都是同一个系列的模型,为什么微调代码不能共用呀? |
想问下大佬,想用多轮对话数据训练chatglm3,应该怎么组织数据呀?魔搭这个文档我没看明白要怎么组织。。。 |
输入格式不一样 |
好东西, mark 一下 |
LLaMA-Factory is all you need: https://github.com/hiyouga/LLaMA-Factory |
@WangRongsheng does LLaMA-Factory support GLM2-6b and using Qlora SFT . in several steps ? |
@LZHgrla how to use xtuner in command line to train my custom dataset , mode is QLora . any guide doc link ? |
Yes, it can do. |
You can try If you have further questions, please post them on here |
@LZHgrla thanks , and i've finally launched up my QLora fine tune . |
marked |
1 similar comment
marked |
使用xtuner train 微调chatglm3后 无法生成 adapter_config.json 导致qlora训练后的权重无法使用@LZHgrla |
+1 |
https://github.com/minghaochen/chatglm3-base-tuning chatglm3发布了,这次还发了base版本的模型,意味着我们可以基于这个base模型去自由地做SFT了。本项目实现了基于base模型的多轮对话SFT。 |
+1 |
我们这边测试并不会出现这个问题,训练后经过转换可以直接获得qlora的adapter权重 |
微调代码什么时候能够发布? |
微调代码已发布,请参考 ChatGLM3-6B 微调示例。 |
关心这个问题,谢谢
The text was updated successfully, but these errors were encountered: