|
Download README.md from LibreYOLO/LibreTinyFormerm: direct link, hf CLI and curl.
- Browser
- Download file 2.36 kB
-
https://huggingface.co/LibreYOLO/LibreTinyFormerm/resolve/main/README.md
- Command line
-
hf download hf://LibreYOLO/LibreTinyFormerm/README.md
-
curl -L -o README.md https://huggingface.co/LibreYOLO/LibreTinyFormerm/resolve/main/README.md
2.36 kB
| license: other | |
| license_name: tinyformer-dinov3 | |
| license_link: LICENSE | |
| library_name: libreyolo | |
| tags: | |
| - object-detection | |
| - tinyformer | |
| # LibreTinyFormerm | |
| TinyFormer-M-PBM detection weights, repackaged for LibreYOLO. | |
| TinyFormer ("TinyFormer: Preserving Tiny Objects in YOLO-DETR Hybrid | |
| Real-time Detectors", arXiv:2605.25046) is a DEIMv2-derived YOLO-DETR hybrid | |
| specialised for tiny objects via a Spatial Semantic Adapter and a 4-scale | |
| Parallel Bi-fusion neck. This size runs on the DEIMv2-distilled ViT-Tiny+ tower (DINOv3-distilled). | |
| Reported COCO val2017 mAP50-95: **53.7**. | |
| ## Usage | |
| ```python | |
| from libreyolo import LibreYOLO | |
| model = LibreYOLO("LibreTinyFormerm.pt") # auto-downloads from this repo | |
| results = model.predict("image.jpg") | |
| ``` | |
| ## Source | |
| Derived from [mmpmmpmmpjosh/TinyFormer](https://github.com/mmpmmpmmpjosh/TinyFormer) | |
| at commit [`9075d9f`](https://github.com/mmpmmpmmpjosh/TinyFormer/commit/9075d9fdf5ce989ca3c7e830a780dfc7fbbe4ec1), | |
| sourced from the official [Google Drive checkpoint mirror](https://drive.google.com/drive/folders/1yIsUO14g5EyTFRbDeISoNJSDqNeSgT5o). | |
| Copyright (C) 2026 AICVlab, National Yang Ming Chiao Tung University (NYCU). | |
| The TinyFormer codebase is licensed under the Apache License, Version 2.0 | |
| (DEIM/DEIMv2 lineage). | |
| The backbone parameters derive from | |
| [facebookresearch/dinov3](https://github.com/facebookresearch/dinov3) | |
| (the DEIMv2-distilled ViT-Tiny+ tower (DINOv3-distilled)) and are licensed under the | |
| [DINOv3 License](https://ai.meta.com/resources/models-and-libraries/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 — learned parameters are unchanged (the EMA | |
| weights of the released solver checkpoint). The wrapper adds ``model_family``, | |
| ``size``, ``nc``, and ``names`` fields so the unified ``LibreYOLO()`` factory | |
| routes correctly without filename heuristics. | |
| See `weights/convert_tinyformer_weights.py` in the | |
| [LibreYOLO source repository](https://github.com/LibreYOLO/libreyolo). | |
| ## License | |
| Dual-licensed: Apache License 2.0 (TinyFormer/DEIMv2 components) and the | |
| DINOv3 License (backbone parameters). The combined LICENSE file in this | |
| repository contains both license texts. See also [`NOTICE`](./NOTICE) for | |
| attribution detail. | |