Add model-index metadata (HF Evaluation Results widget)

README.md

@@ -28,6 +28,32 @@ metrics:
   - f1
 
 base_model: "Roboflow/rf-detr-medium"
+
+model-index:
+  - name: RF-DETR Medium Finetuned on VisDrone-DET
+    results:
+      - task:
+          type: object-detection
+          name: Object Detection
+        dataset:
+          name: VisDrone-DET
+          type: visdrone
+        metrics:
+          - type: mAP50
+            value: 36.82
+            name: mAP@50 (test split)
+          - type: mAP50-95
+            value: 20.14
+            name: mAP@50-95 (test split)
+          - type: precision
+            value: 64.0
+            name: Precision (test split)
+          - type: recall
+            value: 47.05
+            name: Recall (test split)
+        source:
+          url: https://github.com/dronefreak/DetectionBench
+          name: DetectionBench
 ---
 
 
@@ -273,7 +299,6 @@ If you use this model in your research, please consider citing:
 1. The VisDrone-DET dataset (see below)
 2. The original RF-DETR Medium architecture (see below)
 3. DetectionBench, the training/evaluation framework used to produce this checkpoint
-
 ```
 @article{zhu2018vision,
   title={Vision meets drones: A challenge},
@@ -299,7 +324,6 @@ If you use this model in your research, please consider citing:
   year={2023}
 }
 ```
-
 ```bibtex
 @software{Saksena_DetectionBench_2026,
   author = {Saksena, Saumya Kumaar},