Instructions to use HanClinto/CollectorVision with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- CollectorVision
How to use HanClinto/CollectorVision with CollectorVision:
pip install git+https://github.com/HanClinto/CollectorVision huggingface_hub
from huggingface_hub import hf_hub_download import collector_vision as cvg checkpoint = hf_hub_download(repo_id="HanClinto/CollectorVision", filename="model.onnx") # Detector models, such as Cornelius: detector = cvg.NeuralCornerDetector(checkpoint) # Embedder models, such as Milo: embedder = cvg.NeuralEmbedder(checkpoint)
- Notebooks
- Google Colab
- Kaggle
| library_name: onnxruntime | |
| tags: | |
| - collectorvision | |
| - model-registry | |
| # CollectorVision Artifact Registry | |
| This repository is the canonical registry for CollectorVision model artifacts. | |
| It contains metadata only; model binaries remain in their architecture-family | |
| repositories, such as `HanClinto/cornelius` and `HanClinto/milo`. | |
| `registry.json` contains exact model records with immutable Hugging Face commit | |
| revisions, file names, byte sizes, and SHA-256 digests. Its `stable` and | |
| `testing` channels map a model family to a supported exact model ID. | |
| Clients may cache the registry and refresh it periodically. They must download | |
| model artifacts from the recorded immutable revision and verify the SHA-256 | |
| digest before using the file. |