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

[VLLM] Allows for max tokens to be set in model config file #547

Merged
merged 11 commits into from
Feb 12, 2025

Conversation

NathanHB
Copy link
Member

No description provided.

@HuggingFaceDocBuilderDev
Copy link
Collaborator

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

@NathanHB NathanHB merged commit 78b68ab into main Feb 12, 2025
4 checks passed
Comment on lines +319 to +321
sampling_params.max_tokens = (
max_new_tokens if sampling_params.max_tokens is None else sampling_params.max_tokens
)
Copy link

Choose a reason for hiding this comment

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

vLLM has max_tokens as Optional[int] but defaulting to 16 here
That means whenever sampling_params is created, it assumes the value 16 and hence this sampling_params.max_tokens ends up being always equal to 16
Then the lighteval benchmark goes on to warn that the output is not in the Gold Format ...

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.

3 participants