This repository has been archived by the owner on Oct 12, 2023. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 467
为啥照着步骤来,加载dataset example,始终无法加载自定义内容 #2
Labels
solved
This problem has been already solved.
Comments
没有看到详细的报错信息,请问你微调模型了吗。把微调日志发一下。 |
这个只是做个例子。具体微调要准备其他大型数据集,这个示例数据集数据量太小了。 |
用了自己的数据集900条也不出结果,用官方Tuning是可以出来的 |
可以试着增大Lora的 默认参数中为了避免模型发生灾难性遗忘并过拟合到新数据集上,采用的都是较为保守的参数。 |
你好,小白想请教一个问题,这个增大lora的r值具体要怎么做呢?需要加什么参数么? |
@LainNetWork 加入参数--lora_rank=16 |
明白了,感谢回答~ |
您好,我们写了一份关于加载自定义内容的教程文档,请移步:https://github.com/hiyouga/ChatGLM-Efficient-Tuning/blob/main/examples/alter_self_cognition.md |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
The text was updated successfully, but these errors were encountered: