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

[WIP] Standardize inputs and outputs for existing image-text-to-text models #32059

Closed
wants to merge 13 commits into from
Closed

[WIP] Standardize inputs and outputs for existing image-text-to-text models #32059

wants to merge 13 commits into from

Commits on Jul 26, 2024

  1. Add template image-text-to-text pipeline

    @yonigozlan
    yonigozlan committed Jul 26, 2024
    Configuration menu
    Copy the full SHA
    bf2817e View commit details
    Browse the repository at this point in the history

  2. fix style

    @yonigozlan
    yonigozlan committed Jul 26, 2024
    Configuration menu
    Copy the full SHA
    ab0139e View commit details
    Browse the repository at this point in the history

  3. Add processor handling

    @yonigozlan
    yonigozlan committed Jul 26, 2024
    Configuration menu
    Copy the full SHA
    91de714 View commit details
    Browse the repository at this point in the history

  4. Standardise processing donut, git, idefics, pix2struct

    @yonigozlan
    yonigozlan committed Jul 26, 2024
    Configuration menu
    Copy the full SHA
    693f0cd View commit details
    Browse the repository at this point in the history

  5. Fix style and minor issues for idefics and udop

    @yonigozlan
    yonigozlan committed Jul 26, 2024
    Configuration menu
    Copy the full SHA
    68616ec View commit details
    Browse the repository at this point in the history

  6. Add post processing for image-text-to-text models

    @yonigozlan
    yonigozlan committed Jul 26, 2024
    Configuration menu
    Copy the full SHA
    1e4c72a View commit details
    Browse the repository at this point in the history

  7. Add support for batched text and images, and for chat templates with … 

    …images
    @yonigozlan
    yonigozlan committed Jul 26, 2024
    Configuration menu
    Copy the full SHA
    86f3467 View commit details
    Browse the repository at this point in the history

  8. Add support for multiple images per prompt using <image> token, stand… 

    …ardize not returning input prompt in the generated text.
    @yonigozlan
    yonigozlan committed Jul 26, 2024
    Configuration menu
    Copy the full SHA
    469f825 View commit details
    Browse the repository at this point in the history

  9. Fix unbounded variables issue

    @yonigozlan
    yonigozlan committed Jul 26, 2024
    Configuration menu
    Copy the full SHA
    116ea57 View commit details
    Browse the repository at this point in the history

  10. Add tests and fix small issues

    @yonigozlan
    yonigozlan committed Jul 26, 2024
    Configuration menu
    Copy the full SHA
    bb3594e View commit details
    Browse the repository at this point in the history

Commits on Jul 29, 2024

  1. Fix Paligemma prompts with image token

    @yonigozlan
    yonigozlan committed Jul 29, 2024
    Configuration menu
    Copy the full SHA
    a07bbc8 View commit details
    Browse the repository at this point in the history

  2. Fix automated model pipeline test

    @yonigozlan
    yonigozlan committed Jul 29, 2024
    Configuration menu
    Copy the full SHA
    7c14518 View commit details
    Browse the repository at this point in the history

Commits on Aug 6, 2024

  1. Change legacy arg to kwargs

    @yonigozlan
    yonigozlan committed Aug 6, 2024
    Configuration menu
    Copy the full SHA
    5ed6145 View commit details
    Browse the repository at this point in the history