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

DISC-Law-SFT-Triplet 数据集结构 #46

Open
guanidine opened this issue Mar 11, 2024 · 2 comments
Open

DISC-Law-SFT-Triplet 数据集结构 #46

guanidine opened this issue Mar 11, 2024 · 2 comments

Comments

@guanidine
Copy link

您好,您提供的数据集中,DISC-Law-SFT-Triplet 包含 inputoutputreference 三个部分。在用 LLaMA Efficient Tuning 微调时,请问 reference 是如何加入训练的呢?我目前是把它作为 system 输入,或者说这部分应该直接拼接到 input 中?

image image
@yueshengbin
Copy link
Collaborator

如技术报告里说的,reference作为context 拼在input中作为模型输入

@guanidine
Copy link
Author

明白了,谢谢。
顺便想请教一下,您README中给出的LoRA微调的指令,最终得到的结果如何?我在Baichuan2-7B和Qwen1.5-7B两个个模型上分别尝试了LoRA微调,学习率等超参没变,benchmark跑出来比微调前的原始模型要差不少。请问您有在这些模型上测试过吗?

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