Upload README.md with huggingface_hub

README.md

@@ -38,8 +38,8 @@ 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 | 1.607 ms | 0 - 2 MB | FP16 | NPU |  [EfficientNet-B0.tflite](https://huggingface.co/qualcomm/EfficientNet-B0/blob/main/EfficientNet-B0.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.668 ms | 1 - 75 MB | FP16 | NPU |  [EfficientNet-B0.so](https://huggingface.co/qualcomm/EfficientNet-B0/blob/main/EfficientNet-B0.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 1.626 ms | 0 - 2 MB | FP16 | NPU |  [EfficientNet-B0.tflite](https://huggingface.co/qualcomm/EfficientNet-B0/blob/main/EfficientNet-B0.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.668 ms | 0 - 86 MB | FP16 | NPU |  [EfficientNet-B0.so](https://huggingface.co/qualcomm/EfficientNet-B0/blob/main/EfficientNet-B0.so) 
 
 
 
@@ -101,8 +101,8 @@ python -m qai_hub_models.models.efficientnet_b0.export
 Profile Job summary of EfficientNet-B0
 --------------------------------------------------
 Device: SA8255 (Proxy) (13)
-Estimated Inference Time: 1.66 ms
-Estimated Peak Memory Range: 0.61-6.44 MB
+Estimated Inference Time: 1.68 ms
+Estimated Peak Memory Range: 0.00-206.89 MB
 Compute Units: NPU (243) | Total (243)