Upload README.md with huggingface_hub

README.md

@@ -35,7 +35,7 @@ More details on model performance across various devices, can be found
 
 | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
 | ---|---|---|---|---|---|---|---|
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 24.96 ms | 36 - 68 MB | FP16 | GPU |  [Yolo-v7.tflite](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 24.563 ms | 38 - 70 MB | FP16 | GPU |  [Yolo-v7.tflite](https://huggingface.co/qualcomm/Yolo-v7/blob/main/Yolo-v7.tflite) 
 
 
 
@@ -97,9 +97,9 @@ python -m qai_hub_models.models.yolov7.export
 ```
 Profile Job summary of Yolo-v7
 --------------------------------------------------
-Device: SA8775 (Proxy) (13)
-Estimated Inference Time: 24.59 ms
-Estimated Peak Memory Range: 38.27-87.46 MB
+Device: QCS8550 (Proxy) (12)
+Estimated Inference Time: 24.55 ms
+Estimated Peak Memory Range: 38.25-84.52 MB
 Compute Units: GPU (145),CPU (70) | Total (215)