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

Add VLM support #177

Closed

merveenoyan wants to merge 1 commit into huggingface:main from merveenoyan:add_vlm_support

merveenoyan commented Jan 13, 2025

Partially fixes #176 (the latter part where the VLMs are main models for the agents)

For the initial version, we could make some decisions for following questions:

We should give user the option to pass images only for the first step.
We should give user the option to pass images at every step.

It's just a matter of adding image(s) to chat template and keeping image(s) either in memory or passing it all the time.

For later, we could have option for agent to pull more images from somewhere, I just don't know of a use case for this yet.


          initial commit

26c4844

merveenoyan marked this pull request as draft

January 13, 2025 16:49

merveenoyan closed this

Author

merveenoyan commented Jan 16, 2025

closed in favor of #220 to work on the main repo

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet