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

Vision: can I do few shot? #163

Closed
dersuchendee opened this issue Oct 2, 2024 · 1 comment
Closed

Vision: can I do few shot? #163

dersuchendee opened this issue Oct 2, 2024 · 1 comment

Comments

@dersuchendee
Copy link

Can I do few-shot (image+text) to classify a new image with the vision model?
@ashwinb
Copy link
Contributor

ashwinb commented Oct 2, 2024

Not really. Currently we only recommend using max one image in the prompts -- this makes it unsuitable for few-shot usage.

@ashwinb ashwinb closed this as completed Oct 2, 2024
@DanilZittser DanilZittser mentioned this issue Dec 25, 2024
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@ashwinb @dersuchendee