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

set default max_tokens to 1024 #38

Merged
merged 1 commit into from
May 8, 2024
Merged

Conversation

mattf
Copy link
Collaborator

@mattf mattf commented May 8, 2024

if max_tokens is not set the service picks a value. that value is small enough that users report the model is broken or has poor accuracy.

fixes #34

@mattf mattf self-assigned this May 8, 2024
@mattf mattf requested review from raspawar, rlokhande-nv and dglogo May 8, 2024 15:11
@mattf mattf force-pushed the mattf/set-default-max-tokens-1024 branch from a791549 to 0de0ed5 Compare May 8, 2024 15:23
Copy link
Collaborator

@dglogo dglogo left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

lgtm thanks

@mattf mattf merged commit ba7293a into main May 8, 2024
12 checks passed
@mattf mattf deleted the mattf/set-default-max-tokens-1024 branch May 8, 2024 15:58
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

Successfully merging this pull request may close these issues.

Changing max_tokens default value to some higher value may be 512/1024
2 participants