LibreOWLv2b16

OWLv2 base patch-16 ensemble weights mirrored for LibreYOLO's LibreOpenVocab tier.

Source

Mirrored from google/owlv2-base-patch16-ensemble. The model weights are published by Google LLC under the Apache License 2.0.

Paper: https://arxiv.org/abs/2306.09683

Modifications

No learned parameters were changed. This repository preserves the Hugging Face transformers snapshot files needed by LibreYOLO's open-vocabulary detector wrapper and replaces the model card with LibreYOLO-specific loading notes.

Usage

from libreyolo import LibreOpenVocab

model = LibreOpenVocab("LibreOWLv2b16")
model.set_classes(["person", "dog", "car"])
results = model.predict("image.jpg")