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

构造数据集的时候 可以使用glm4代替gpt4吗 #13

Open
Guodashen222 opened this issue Mar 19, 2024 · 3 comments
Open

构造数据集的时候 可以使用glm4代替gpt4吗 #13

Guodashen222 opened this issue Mar 19, 2024 · 3 comments

Comments

@Guodashen222
Copy link

No description provided.

@qijimrc
Copy link
Collaborator

qijimrc commented Mar 20, 2024

我们早期对比了ChatGLM-3和GPT4,实验发现后者效果更好。不过目前针对Question描述比较清楚的VQA数据,我们认为可以使用GLM4生成文本推理步骤。

@terryII
Copy link

terryII commented Apr 12, 2024

我注意到在cogcom/data/tools/gpt4.py中调用的模型api为gpt-3.5-turbo而不是gpt4,考虑到api的费用问题,是不是可以用gpt-3.5-turbo生成的com数据就能达到较为理想的效果? @qijimrc

@qijimrc
Copy link
Collaborator

qijimrc commented Apr 13, 2024

我注意到在cogcom/data/tools/gpt4.py中调用的模型api为gpt-3.5-turbo而不是gpt4,考虑到api的费用问题,是不是可以用gpt-3.5-turbo生成的com数据就能达到较为理想的效果? @qijimrc

Hi terry, 针对问题描述较为清楚的VQA数据,采用gpt-3.5-turbo也能获得较多的positive chains(我们测试GPT4生成positive chains的占比在35%左右,可以作为对比)。

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

3 participants