Upload README.md with huggingface_hub

README.md

@@ -34,7 +34,8 @@ 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 | 47.978 ms | 0 - 9 MB | FP16 | NPU |  [DETR-ResNet101.tflite](https://huggingface.co/qualcomm/DETR-ResNet101/blob/main/DETR-ResNet101.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 24.664 ms | 0 - 4 MB | FP16 | NPU |  [DETR-ResNet101.tflite](https://huggingface.co/qualcomm/DETR-ResNet101/blob/main/DETR-ResNet101.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 21.04 ms | 3 - 30 MB | FP16 | NPU |  [DETR-ResNet101.so](https://huggingface.co/qualcomm/DETR-ResNet101/blob/main/DETR-ResNet101.so) 
 
 
 ## Installation
@@ -95,10 +96,10 @@ python -m qai_hub_models.models.detr_resnet101.export
 ```
 Profile Job summary of DETR-ResNet101
 --------------------------------------------------
-Device: QCS8550 (Proxy) (12)
-Estimated Inference Time: 48.06 ms
-Estimated Peak Memory Range: 1.32-11.86 MB
-Compute Units: NPU (910),GPU (2) | Total (912)
+Device: Snapdragon X Elite CRD (11)
+Estimated Inference Time: 31.21 ms
+Estimated Peak Memory Range: 2.64-2.64 MB
+Compute Units: NPU (1084) | Total (1084)
 
 
 ```