Skip to content
This repository has been archived by the owner on Oct 6, 2023. It is now read-only.

奖励模型用的什么数据集啊 #6

Closed
ScienGU opened this issue May 19, 2023 · 3 comments
Closed

奖励模型用的什么数据集啊 #6

ScienGU opened this issue May 19, 2023 · 3 comments
Labels
question Further information is requested

Comments

@ScienGU
Copy link

ScienGU commented May 19, 2023

No description provided.

@WangRongsheng
Copy link
Owner

使用这个数据集：https://github.com/WangRongsheng/MedQA-ChatGLM/blob/main/data/dataset_info-plus.json#L23

@WangRongsheng WangRongsheng added the question Further information is requested label May 19, 2023
@ScienGU
Copy link
Author

ScienGU commented May 19, 2023

使用这个数据集：https://github.com/WangRongsheng/MedQA-ChatGLM/blob/main/data/dataset_info-plus.json#L23

谢谢，请问最后强化学习后，效果怎么样？

@WangRongsheng
Copy link
Owner

效果会有所提升，我们并没有开放RLHF训练的权重。

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Assignees
No one assigned
Labels
question Further information is requested
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@WangRongsheng @ScienGU