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

Fix llava #1149

Merged
merged 1 commit into from
Dec 12, 2024
Merged

Fix llava #1149

merged 1 commit into from
Dec 12, 2024

Conversation

awni
Copy link
Member

@awni awni commented Dec 10, 2024

Closes #1138

Looks like the HF preprocessor changed behavior, so this PR accommodates that.

Comment on lines +192 to +193
prompt = codecs.decode(args.prompt, "unicode_escape")

Copy link
Member Author

Choose a reason for hiding this comment

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

This is a random addition, but it lets you do things like Hello\nworld on the CLI and have the return character be parsed correctly.

Copy link
Member

@angeloskath angeloskath left a comment

Choose a reason for hiding this comment

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

👍

@awni awni merged commit 77b42b7 into main Dec 12, 2024
2 checks passed
@awni awni deleted the fix_llava branch December 12, 2024 18:37
mokeddembillel pushed a commit to mokeddembillel/mlx-examples that referenced this pull request Dec 16, 2024
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.

ValueError: The number of image tokens (576) does not match the number of image inputs (1).
2 participants