Upload README.md with huggingface_hub

README.md

@@ -12,6 +12,8 @@ datasets:
 
 # VisionQC EfficientAD-medium for VisA/pcb1
 
+[![GitHub](https://img.shields.io/badge/GitHub-VisionQC-181717?logo=github)](https://github.com/pnthang04/VisionQC)
+
 EfficientAD-medium anomaly detection checkpoint trained with Anomalib 2.6.0
 on the `pcb1` category of VisA.
 
@@ -57,11 +59,22 @@ batch-size-1 EfficientAD baseline.
 
 ## Loading
 
-Use this checkpoint with the VisionQC project and Anomalib 2.6.0:
+Download the checkpoint:
+
+```bash
+hf download thangkt/visionqc-efficientad-medium-pcb1 model-best.ckpt \
+  --local-dir weights/efficientad-medium-pcb1
+```
+
+Use it with the VisionQC project and Anomalib 2.6.0:
 
 ```bash
-visionqc evaluate --checkpoint /path/to/model-best.ckpt
+visionqc evaluate \
+  --checkpoint weights/efficientad-medium-pcb1/model-best.ckpt
 ```
 
-The corresponding source project is available at
-https://github.com/pnthang04/VisionQC.
+## Links
+
+- Source: https://github.com/pnthang04/VisionQC
+- Multi-GPU training PR: https://github.com/pnthang04/VisionQC/pull/1
+- Model repository: https://huggingface.co/thangkt/visionqc-efficientad-medium-pcb1