Upload README.md with huggingface_hub

README.md

@@ -32,8 +32,8 @@ 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 | 1.398 ms | 0 - 8 MB | FP16 | NPU |  [QuickSRNetMedium.tflite](https://huggingface.co/qualcomm/QuickSRNetMedium/blob/main/QuickSRNetMedium.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.989 ms | 0 - 7 MB | FP16 | NPU |  [QuickSRNetMedium.so](https://huggingface.co/qualcomm/QuickSRNetMedium/blob/main/QuickSRNetMedium.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 1.386 ms | 0 - 8 MB | FP16 | NPU |  [QuickSRNetMedium.tflite](https://huggingface.co/qualcomm/QuickSRNetMedium/blob/main/QuickSRNetMedium.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.998 ms | 0 - 7 MB | FP16 | NPU |  [QuickSRNetMedium.so](https://huggingface.co/qualcomm/QuickSRNetMedium/blob/main/QuickSRNetMedium.so) 
 
 
 ## Installation
@@ -94,16 +94,16 @@ python -m qai_hub_models.models.quicksrnetmedium.export
 Profile Job summary of QuickSRNetMedium
 --------------------------------------------------
 Device: Samsung Galaxy S24 (14)
-Estimated Inference Time: 0.94 ms
-Estimated Peak Memory Range: 0.02-18.72 MB
+Estimated Inference Time: 0.90 ms
+Estimated Peak Memory Range: 0.02-18.70 MB
 Compute Units: NPU (14),CPU (3) | Total (17)
 
 Profile Job summary of QuickSRNetMedium
 --------------------------------------------------
 Device: Samsung Galaxy S24 (14)
 Estimated Inference Time: 0.65 ms
-Estimated Peak Memory Range: 0.20-13.56 MB
-Compute Units: NPU (18) | Total (18)
+Estimated Peak Memory Range: 0.20-14.70 MB
+Compute Units: NPU (17) | Total (17)
 
 
 ```