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

What is the purpose of finetuned parameter in LlamaDynamicYaRNScaledRotaryEmbedding? #36

Open
fahadh4ilyas opened this issue Nov 6, 2023 · 0 comments
Open

What is the purpose of finetuned parameter in LlamaDynamicYaRNScaledRotaryEmbedding? #36

fahadh4ilyas opened this issue Nov 6, 2023 · 0 comments

Comments

@fahadh4ilyas
Copy link

I see that in __init__ method of LlamaDynamicYaRNScaledRotaryEmbedding there is a parameter called finetuned which is a boolean. What is the purpose of that parameter? Should we set it to False while finetuning the model and then set it to True for inference after finetuning? What could be the problem if we keep it False regardless the model is finetuned or not?
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
@fahadh4ilyas