Upload README.md with huggingface_hub

README.md

@@ -37,8 +37,8 @@ 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 | 0.427 ms | 0 - 14 MB | INT8 | NPU |  [ResNet18Quantized.tflite](https://huggingface.co/qualcomm/ResNet18Quantized/blob/main/ResNet18Quantized.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.633 ms | 0 - 58 MB | INT8 | NPU |  [ResNet18Quantized.so](https://huggingface.co/qualcomm/ResNet18Quantized/blob/main/ResNet18Quantized.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.421 ms | 0 - 14 MB | INT8 | NPU |  [ResNet18Quantized.tflite](https://huggingface.co/qualcomm/ResNet18Quantized/blob/main/ResNet18Quantized.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.636 ms | 0 - 28 MB | INT8 | NPU |  [ResNet18Quantized.so](https://huggingface.co/qualcomm/ResNet18Quantized/blob/main/ResNet18Quantized.so) 
 
 
 ## Installation
@@ -98,17 +98,10 @@ python -m qai_hub_models.models.resnet18_quantized.export
 ```
 Profile Job summary of ResNet18Quantized
 --------------------------------------------------
-Device: QCS8550 (Proxy) (12)
-Estimated Inference Time: 0.46 ms
-Estimated Peak Memory Range: 0.02-14.48 MB
-Compute Units: NPU (41) | Total (41)
-
-Profile Job summary of ResNet18Quantized
---------------------------------------------------
-Device: QCS8550 (Proxy) (12)
-Estimated Inference Time: 0.68 ms
-Estimated Peak Memory Range: 0.02-57.95 MB
-Compute Units: NPU (39) | Total (39)
+Device: Snapdragon X Elite CRD (11)
+Estimated Inference Time: 0.77 ms
+Estimated Peak Memory Range: 0.54-0.54 MB
+Compute Units: NPU (37) | Total (37)
 
 
 ```