Instructions to use LibreYOLO/LibreDEIMv2m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LibreYOLO
How to use LibreYOLO/LibreDEIMv2m with LibreYOLO:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
LibreDEIMv2m
DEIMv2-m (DINOv3-derived backbone) detection weights, repackaged for LibreYOLO.
Reported COCO val2017 mAP50-95: 53.0.
Source
Derived from Intellindust-AI-Lab/DEIMv2
at commit 0fff8d4,
sourced from the upstream HuggingFace release
Intellindust/DEIMv2_DINOv3_M_COCO.
Copyright (C) Intellindust Information Technology (Shenzhen) Co., Ltd.
The DEIMv2 codebase is licensed under the Apache License, Version 2.0.
The backbone parameters are derived from facebookresearch/dinov3 and are licensed under the DINOv3 License. Because this checkpoint bundles DINOv3-derived parameters, the combined distribution is governed by the terms of both licenses.
Modifications
Checkpoint metadata wrapping only β learned parameters are unchanged.
The wrapper adds model_family, size, nc, and names fields so the
unified LibreYOLO() factory routes correctly without filename heuristics.
See weights/convert_deimv2_weights.py in the
LibreYOLO source repository.
Usage
pip install libreyolo
from libreyolo import LibreYOLO
model = LibreYOLO("LibreDEIMv2m.pt")
results = model("image.jpg", save=True)
License
Dual-licensed: Apache License 2.0 (DEIMv2 components) and the DINOv3 License
(backbone parameters). The combined LICENSE file in this repository contains
both license texts. See also NOTICE for attribution detail.
- Downloads last month
- 141