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 | 61.028 ms | 0 - 3 MB | FP16 | NPU |  [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 38.211 ms | 0 - 7 MB | FP16 | NPU |  [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 31.64 ms | 0 - 47 MB | FP16 | NPU |  [Swin-Base.so](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.so) 
 
 
 ## Installation
@@ -96,10 +97,10 @@ python -m qai_hub_models.models.swin_base.export
 ```
 Profile Job summary of Swin-Base
 --------------------------------------------------
-Device: QCS8550 (Proxy) (12)
-Estimated Inference Time: 61.65 ms
-Estimated Peak Memory Range: 0.03-3.13 MB
-Compute Units: NPU (1568) | Total (1568)
+Device: Snapdragon X Elite CRD (11)
+Estimated Inference Time: 38.97 ms
+Estimated Peak Memory Range: 0.57-0.57 MB
+Compute Units: NPU (1255) | Total (1255)
 
 
 ```