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

llm-tool: fix prompt from file #176

Merged
merged 3 commits into from
Jan 8, 2025

Conversation

pcuenca
Copy link
Contributor

@pcuenca pcuenca commented Jan 7, 2025

According to the documentation, @ can be used to indicate input files for the prompt, but resolvePrompt was never being called.

Tested before / after with

./mlx-run llm-tool eval --model mlx-community/gemma-2-2b-it-4bit --prompt @prompt.txt

Copy link
Collaborator

@davidkoski davidkoski left a comment

Choose a reason for hiding this comment

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

Thanks for catching that! I think it must have been removed in the vlm refactor.

@davidkoski
Copy link
Collaborator

CI is failing on the swift-format check -- can you please run: https://github.com/ml-explore/mlx-swift-examples/blob/main/CONTRIBUTING.md#pull-requests

Thank you!

@pcuenca
Copy link
Contributor Author

pcuenca commented Jan 8, 2025

Done, sorry about that!

@davidkoski davidkoski merged commit 2f1928b into ml-explore:main Jan 8, 2025
3 checks passed
@pcuenca pcuenca deleted the fix-prompt-from-file branch January 8, 2025 16:43
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.

2 participants