fix: set library_name to ultralytics to restore download tracking

fix: add base_model_relation: finetune to override ONNX-induced quantized inference

feat: add ONNX export (opset 12, 1920x1920, 46 MB)

docs: add ONNX inference section to model card

fix: switch library_name to pytorch, add num_parameters, add ultralytics tag

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Update README.md

Upload folder using huggingface_hub

initial commit