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 | 1.171 ms | 0 - 2 MB | INT8 | NPU |  [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.394 ms | 0 - 178 MB | INT8 | NPU |  [ResNet101Quantized.so](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 1.181 ms | 0 - 2 MB | INT8 | NPU |  [ResNet101Quantized.tflite](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.381 ms | 0 - 8 MB | INT8 | NPU |  [ResNet101Quantized.so](https://huggingface.co/qualcomm/ResNet101Quantized/blob/main/ResNet101Quantized.so) 
 
 
 ## Installation
@@ -98,17 +98,10 @@ python -m qai_hub_models.models.resnet101_quantized.export
 ```
 Profile Job summary of ResNet101Quantized
 --------------------------------------------------
-Device: QCS8550 (Proxy) (12)
-Estimated Inference Time: 1.20 ms
-Estimated Peak Memory Range: 0.02-2.02 MB
-Compute Units: NPU (150) | Total (150)
-
-Profile Job summary of ResNet101Quantized
---------------------------------------------------
-Device: QCS8550 (Proxy) (12)
-Estimated Inference Time: 1.43 ms
-Estimated Peak Memory Range: 0.06-10.32 MB
-Compute Units: NPU (148) | Total (148)
+Device: Snapdragon X Elite CRD (11)
+Estimated Inference Time: 1.41 ms
+Estimated Peak Memory Range: 0.34-0.34 MB
+Compute Units: NPU (146) | Total (146)
 
 
 ```