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

fix the deepseekcoder template to avoid repeat problem #5072

Merged
merged 3 commits into from
Aug 9, 2024

Conversation

relic-yuexi
Copy link
Contributor

What does this PR do?

I fixed the template for DeepSeek-Coder. The reference link for the template is as follows:

https://github.com/deepseek-ai/DeepSeek-Coder/blob/b7ba565956fe61153064f288862daf1896de5393/finetune/finetune_deepseekcoder.py#L16

The main change was the addition of the "<|EOT|>" token, which ensures that the trained model does not generate infinitely due to the lack of an end-of-sequence marker. I have trained the relevant models and compared them, finding that the new version of the template perfectly solves the problem.

Before submitting

@hiyouga
Copy link
Owner

hiyouga commented Aug 9, 2024

Nice catch

@hiyouga hiyouga merged commit 984961c into hiyouga:main Aug 9, 2024
1 check passed
@hiyouga hiyouga added the solved This problem has been already solved label Aug 9, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
solved This problem has been already solved
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants