Upload README.md with huggingface_hub

README.md

@@ -34,8 +34,8 @@ 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 | 3.434 ms | 0 - 2 MB | FP16 | NPU |  [Midas-V2.tflite](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 3.388 ms | 1 - 25 MB | FP16 | NPU |  [Midas-V2.so](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 3.191 ms | 0 - 2 MB | FP16 | NPU |  [Midas-V2.tflite](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 3.295 ms | 0 - 45 MB | FP16 | NPU |  [Midas-V2.so](https://huggingface.co/qualcomm/Midas-V2/blob/main/Midas-V2.so) 
 
 
 
@@ -98,9 +98,9 @@ python -m qai_hub_models.models.midas.export
 Profile Job summary of Midas-V2
 --------------------------------------------------
 Device: Snapdragon X Elite CRD (11)
-Estimated Inference Time: 3.41 ms
+Estimated Inference Time: 3.28 ms
 Estimated Peak Memory Range: 0.75-0.75 MB
-Compute Units: NPU (198) | Total (198)
+Compute Units: NPU (197) | Total (197)
 
 
 ```