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

[QUESTION]convert LLaMA2-7B to the Megatron format failed: the converted model only repeats meaningless numbers #1365

Open
carrot0117 opened this issue Jan 22, 2025 · 0 comments

Comments

@carrot0117
Copy link

When I converted the LLaMA2-7B model to the Megatron format, the program ran successfully and provided the converted model. However, the converted model cannot provide meaningful answers to questions and only repeats meaningless numbers. The original LLaMA2 model was able to respond to questions correctly. Below are the conversion script and the output log file. Is there any good way to solve this issue?

convert-hf-to-megatron-0121-7b.log

convert_hf_to_megatron.sh.txt

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

1 participant