Gemma 4 E2B instruct weights mirrored for LibreYOLO's LibreVLM tier.
Mirrored from
google/gemma-4-E2B-it
at commit
3e22461f65e89153144f8adb70e3b8c2cc9845a7.
Copyright (c) Google DeepMind. Licensed under the Apache License 2.0.
No learned parameters were changed. This repository preserves the Hugging Face
snapshot files needed by LibreYOLO's VLM wrapper and replaces the model card
with LibreYOLO-specific loading notes.
1from libreyolo import LibreVLM
2
3model = LibreVLM("gemma-4-e2b")
4model.set_classes(["person", "helmet"])
5results = model.predict("image.jpg")
