-
Notifications
You must be signed in to change notification settings - Fork 72
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
Does LLaVA-Next support in-context(few-shot) inference? #61
Comments
Also very interested in this for few-shot image classification. So far, I haven't been able to get good results. Is it possible to do it with LLaVA-NeXT out of the box, or would it need fine tune for this use? |
same here, hope the authors can have some feedback |
The recently released LLaVA-NeXT (Interleave) supports the a variety of daily-life multi-image scenarios, but it is NOT specifically trained for in-context-learning. |
I use this script for inference, but the model can only outputs "<|im_end|>". What's wrong with my script? Thanks a lot for help! @ChunyuanLI |
Thanks for your work! Can I input multi-images and multi-instructions for few-shot inference?
The text was updated successfully, but these errors were encountered: