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

Support precise tokenizer for LLama 3 models #103

Open
adubovik opened this issue May 3, 2024 · 0 comments
Open

Support precise tokenizer for LLama 3 models #103

adubovik opened this issue May 3, 2024 · 0 comments
Assignees
@roman-romanov-o

Comments

@adubovik
Copy link
Collaborator

adubovik commented May 3, 2024

Currrently Llama 3 /tokenize endpoint uses conservative byte-count estimation for a number of tokens.
See how tokenizer is defined in the Llama 3 repo for a reference.
Use the tokenizer from HF.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@roman-romanov-o roman-romanov-o

Labels
None yet
Projects
AI DIAL
Status: No status
Milestone
No milestone
Development

No branches or pull requests
2 participants
@adubovik @roman-romanov-o