Skip to content

This issue was moved to a discussion.

You can continue the conversation there. Go to discussion →

Why is it necessary to include b" " before the prompt for tokenization? #537

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
Closed
viniciusarruda opened this issue Jul 27, 2023 · 0 comments
Closed

Why is it necessary to include b" " before the prompt for tokenization? #537

viniciusarruda opened this issue Jul 27, 2023 · 0 comments

Comments

@viniciusarruda
Copy link
Contributor

How you figured out that it was needed to include a b" " in front of the prompt for tokenization to be similar to Meta tokenization?

I think this might solve an issue in the original llama.cpp repo.
@viniciusarruda viniciusarruda changed the title Why needs to include b" " in tokenization? Why is it necessary to include b" " before the prompt for tokenization? Jul 27, 2023
Repository owner locked and limited conversation to collaborators Jul 30, 2023
@gjmulder gjmulder converted this issue into discussion #545 Jul 30, 2023

This issue was moved to a discussion.

You can continue the conversation there. Go to discussion →

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@viniciusarruda