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 | 159.721 ms | 6 - 220 MB | FP16 | NPU |  [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 143.885 ms | 9 - 35 MB | FP16 | NPU |  [Unet-Segmentation.so](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 155.616 ms | 6 - 219 MB | FP16 | NPU |  [Unet-Segmentation.tflite](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 150.609 ms | 9 - 32 MB | FP16 | NPU |  [Unet-Segmentation.so](https://huggingface.co/qualcomm/Unet-Segmentation/blob/main/Unet-Segmentation.so) 
 
 
 ## Installation
@@ -92,23 +92,6 @@ device. This script does the following:
 python -m qai_hub_models.models.unet_segmentation.export
 ```
 
-```
-Profile Job summary of Unet-Segmentation
---------------------------------------------------
-Device: Samsung Galaxy S24 (14)
-Estimated Inference Time: 113.23 ms
-Estimated Peak Memory Range: 4.46-345.06 MB
-Compute Units: NPU (31) | Total (31)
-
-Profile Job summary of Unet-Segmentation
---------------------------------------------------
-Device: Samsung Galaxy S24 (14)
-Estimated Inference Time: 110.49 ms
-Estimated Peak Memory Range: 9.41-107.93 MB
-Compute Units: NPU (51) | Total (51)
-
-
-```
 ## How does this work?
 
 This [export script](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/Unet-Segmentation/export.py)