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 | 28.481 ms | 0 - 71 MB | FP16 | NPU |  [Swin-Tiny.tflite](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 17.594 ms | 0 - 3 MB | FP16 | NPU |  [Swin-Tiny.tflite](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 15.006 ms | 0 - 27 MB | FP16 | NPU |  [Swin-Tiny.so](https://huggingface.co/qualcomm/Swin-Tiny/blob/main/Swin-Tiny.so) 
 
 
 ## Installation
@@ -96,10 +97,10 @@ python -m qai_hub_models.models.swin_tiny.export
 ```
 Profile Job summary of Swin-Tiny
 --------------------------------------------------
-Device: QCS8550 (Proxy) (12)
-Estimated Inference Time: 28.41 ms
-Estimated Peak Memory Range: 0.05-2.97 MB
-Compute Units: NPU (837) | Total (837)
+Device: Snapdragon X Elite CRD (11)
+Estimated Inference Time: 14.25 ms
+Estimated Peak Memory Range: 0.57-0.57 MB
+Compute Units: NPU (700) | Total (700)
 
 
 ```