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

如何接入ChatGLM呢 #18

Open
Yewx0310 opened this issue Jul 20, 2023 · 7 comments
Open

如何接入ChatGLM呢 #18

Yewx0310 opened this issue Jul 20, 2023 · 7 comments

Comments

@Yewx0310
Copy link

No description provided.

@Nydaym
Copy link

Nydaym commented Sep 11, 2023

直接把推理部分改成chatglm的就可以了,不过由于GLM的能力比ChatGPT弱需要修改一下提示词,我测试的是oneshot能够学习格式,但是生成的质量比较差,后面还会试试llama的生成效果如何,只能说跟监督学习比起来还是差挺多,但是胜在能够做很多不同的领域语料,而且可以通过lora微调glm来进行特定领域的微调,这个库我觉得还是主要做格式后处理。

@chenylong
Copy link

每个模型对提示词的反馈都不一样呀,好难受

@Yewx0310
Copy link
Author

Yewx0310 commented Sep 27, 2023 via email

@lawliet1777
Copy link

试了baichuan2的效果一般 加上few-shot应该会好些

@Yewx0310
Copy link
Author

Yewx0310 commented Nov 3, 2023 via email

@Yewx0310
Copy link
Author

Yewx0310 commented Nov 3, 2023

试了baichuan2的效果一般 加上few-shot应该会好些
在开放领域的效果可以吗?不知道baichuan和chatglm到底哪个好一些

@Nydaym
Copy link

Nydaym commented Nov 3, 2023

试了baichuan2的效果一般 加上few-shot应该会好些
在开放领域的效果可以吗?不知道baichuan和chatglm到底哪个好一些

试试新出的GLM3呢?不过我觉得可能都差不多毕竟参数量在那摆着呢。

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

4 participants