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 | 1.943 ms | 0 - 3 MB | FP16 | NPU |  [DenseNet-121.tflite](https://huggingface.co/qualcomm/DenseNet-121/blob/main/DenseNet-121.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.986 ms | 1 - 40 MB | FP16 | NPU |  [DenseNet-121.so](https://huggingface.co/qualcomm/DenseNet-121/blob/main/DenseNet-121.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 1.939 ms | 0 - 2 MB | FP16 | NPU |  [DenseNet-121.tflite](https://huggingface.co/qualcomm/DenseNet-121/blob/main/DenseNet-121.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.984 ms | 0 - 28 MB | FP16 | NPU |  [DenseNet-121.so](https://huggingface.co/qualcomm/DenseNet-121/blob/main/DenseNet-121.so) 
 
 
 
@@ -101,8 +101,8 @@ python -m qai_hub_models.models.densenet121.export
 Profile Job summary of DenseNet-121
 --------------------------------------------------
 Device: SA8255 (Proxy) (13)
-Estimated Inference Time: 1.98 ms
-Estimated Peak Memory Range: 0.01-27.77 MB
+Estimated Inference Time: 1.99 ms
+Estimated Peak Memory Range: 0.01-6.82 MB
 Compute Units: NPU (372) | Total (372)