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.

Sign up for GitHub

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

Jump to bottom

你们博客中的CoT SFT数据集会开源吗？ #130

Open
chiaitian opened this issue Feb 24, 2025 · 0 comments
Open

你们博客中的CoT SFT数据集会开源吗？ #130

chiaitian opened this issue Feb 24, 2025 · 0 comments

Comments

@chiaitian
Copy link

你们博客中的CoT SFT数据集会开源吗？像这样的

Example: 
<think> object 1, (272, 540), a yellow sphere \n object 2, (525, 356), a cyan cylinder \n object 3, (408, 359), a gray sphere</think> <answer> 3 </answer>

另外，我觉得直接在Clevr_CoGenT_TrainA_R1上SFT可能不是很合理吧。R1的输入有场景描述，输出的think也是基于这个场景描述的。而在Clevr_CoGenT_TrainA_R1上SFT时，输入没有场景描述，监督的也有很多提到这个场景描述。
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@chiaitian