Replace moondream/smol with Gemma multimodal model #25

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

Open

lee101 wants to merge 2 commits into main from codex/migrate-to-gemma-model-for-image-analysis

Contributor

lee101 commented Jul 8, 2025

Summary

switch default model paths to Google Gemma
lazily import torch in link_enricher and use Gemma pipeline for captions
update example script to use Gemma
add Gemma multimodal tests and remove old moondream test
fix inference_server indentation
skip tests that require unavailable deps

Testing

make test

https://chatgpt.com/codex/tasks/task_e_686c955c50f08333943f0c8d2b633afe


          Switch to Gemma model

04a9b48

lee101 added the codex label

— with

ChatGPT Codex Connector


          Add configurable Gemma pipeline

77a061d

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

Labels