Upload README.md with huggingface_hub

README.md

@@ -39,8 +39,8 @@ 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 | 0.814 ms | 0 - 2 MB | INT8 | NPU |  [ResNet50Quantized.tflite](https://huggingface.co/qualcomm/ResNet50Quantized/blob/main/ResNet50Quantized.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.997 ms | 0 - 7 MB | INT8 | NPU |  [ResNet50Quantized.so](https://huggingface.co/qualcomm/ResNet50Quantized/blob/main/ResNet50Quantized.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.794 ms | 0 - 2 MB | INT8 | NPU |  [ResNet50Quantized.tflite](https://huggingface.co/qualcomm/ResNet50Quantized/blob/main/ResNet50Quantized.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.996 ms | 0 - 32 MB | INT8 | NPU |  [ResNet50Quantized.so](https://huggingface.co/qualcomm/ResNet50Quantized/blob/main/ResNet50Quantized.so) 
 
 
 
@@ -103,8 +103,8 @@ python -m qai_hub_models.models.resnet50_quantized.export
 Profile Job summary of ResNet50Quantized
 --------------------------------------------------
 Device: SA8255 (Proxy) (13)
-Estimated Inference Time: 0.99 ms
-Estimated Peak Memory Range: 0.00-178.32 MB
+Estimated Inference Time: 1.00 ms
+Estimated Peak Memory Range: 0.16-6.42 MB
 Compute Units: NPU (78) | Total (78)