Upload README.md with huggingface_hub

README.md

@@ -35,7 +35,8 @@ 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 | 11.504 ms | 0 - 2 MB | FP16 | NPU |  [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 5.71 ms | 0 - 2 MB | FP16 | NPU |  [ConvNext-Tiny.tflite](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 3.79 ms | 0 - 163 MB | FP16 | NPU |  [ConvNext-Tiny.so](https://huggingface.co/qualcomm/ConvNext-Tiny/blob/main/ConvNext-Tiny.so) 
 
 
 ## Installation
@@ -95,10 +96,10 @@ python -m qai_hub_models.models.convnext_tiny.export
 ```
 Profile Job summary of ConvNext-Tiny
 --------------------------------------------------
-Device: Samsung Galaxy S24 (14)
-Estimated Inference Time: 8.14 ms
-Estimated Peak Memory Range: 0.02-199.53 MB
-Compute Units: NPU (380) | Total (380)
+Device: Snapdragon X Elite CRD (11)
+Estimated Inference Time: 3.95 ms
+Estimated Peak Memory Range: 0.57-0.57 MB
+Compute Units: NPU (223) | Total (223)
 
 
 ```