Upload README.md with huggingface_hub

README.md

@@ -32,8 +32,8 @@ 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 | 8.557 ms | 0 - 7 MB | FP16 | NPU |  [FCN_ResNet50.tflite](https://huggingface.co/qualcomm/FCN_ResNet50/blob/main/FCN_ResNet50.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 7.883 ms | 0 - 10 MB | FP16 | NPU |  [FCN_ResNet50.so](https://huggingface.co/qualcomm/FCN_ResNet50/blob/main/FCN_ResNet50.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 8.481 ms | 4 - 6 MB | FP16 | NPU |  [FCN_ResNet50.tflite](https://huggingface.co/qualcomm/FCN_ResNet50/blob/main/FCN_ResNet50.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 7.915 ms | 0 - 14 MB | FP16 | NPU |  [FCN_ResNet50.so](https://huggingface.co/qualcomm/FCN_ResNet50/blob/main/FCN_ResNet50.so) 
 
 
 ## Installation
@@ -90,23 +90,6 @@ device. This script does the following:
 python -m qai_hub_models.models.fcn_resnet50.export
 ```
 
-```
-Profile Job summary of FCN_ResNet50
---------------------------------------------------
-Device: Samsung Galaxy S24 (14)
-Estimated Inference Time: 6.32 ms
-Estimated Peak Memory Range: 2.09-74.82 MB
-Compute Units: NPU (84) | Total (84)
-
-Profile Job summary of FCN_ResNet50
---------------------------------------------------
-Device: Samsung Galaxy S24 (14)
-Estimated Inference Time: 5.82 ms
-Estimated Peak Memory Range: 0.59-56.95 MB
-Compute Units: NPU (125) | Total (125)
-
-
-```
 ## How does this work?
 
 This [export script](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/FCN_ResNet50/export.py)