Upload README.md with huggingface_hub

README.md

@@ -36,7 +36,8 @@ 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 | 4.395 ms | 0 - 2 MB | INT8 | NPU |  [Yolo-v7-Quantized.tflite](https://huggingface.co/qualcomm/Yolo-v7-Quantized/blob/main/Yolo-v7-Quantized.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 4.43 ms | 0 - 143 MB | INT8 | NPU |  [Yolo-v7-Quantized.tflite](https://huggingface.co/qualcomm/Yolo-v7-Quantized/blob/main/Yolo-v7-Quantized.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 4.818 ms | 0 - 10 MB | INT8 | NPU | Yolo-v7-Quantized 
 
 
 
@@ -98,10 +99,10 @@ python -m qai_hub_models.models.yolov7_quantized.export
 ```
 Profile Job summary of Yolo-v7-Quantized
 --------------------------------------------------
-Device: RB5 (Proxy) (12)
-Estimated Inference Time: 96.70 ms
-Estimated Peak Memory Range: 8.69-27.21 MB
-Compute Units: NPU (32),GPU (127),CPU (70) | Total (229)
+Device: Snapdragon X Elite CRD (11)
+Estimated Inference Time: 3.88 ms
+Estimated Peak Memory Range: 1.18-1.18 MB
+Compute Units: NPU (221) | Total (221)
 
 
 ```