Upload README.md with huggingface_hub

README.md

@@ -36,8 +36,8 @@ 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 | 4.786 ms | 0 - 163 MB | FP16 | NPU |  [WideResNet50.tflite](https://huggingface.co/qualcomm/WideResNet50/blob/main/WideResNet50.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 4.614 ms | 1 - 300 MB | FP16 | NPU |  [WideResNet50.so](https://huggingface.co/qualcomm/WideResNet50/blob/main/WideResNet50.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 4.9 ms | 0 - 2 MB | FP16 | NPU |  [WideResNet50.tflite](https://huggingface.co/qualcomm/WideResNet50/blob/main/WideResNet50.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 5.767 ms | 1 - 249 MB | FP16 | NPU |  [WideResNet50.so](https://huggingface.co/qualcomm/WideResNet50/blob/main/WideResNet50.so) 
 
 
 ## Installation
@@ -94,23 +94,6 @@ device. This script does the following:
 python -m qai_hub_models.models.wideresnet50.export
 ```
 
-```
-Profile Job summary of WideResNet50
---------------------------------------------------
-Device: Samsung Galaxy S24 (14)
-Estimated Inference Time: 3.60 ms
-Estimated Peak Memory Range: 0.02-91.57 MB
-Compute Units: NPU (77) | Total (77)
-
-Profile Job summary of WideResNet50
---------------------------------------------------
-Device: Samsung Galaxy S24 (14)
-Estimated Inference Time: 3.41 ms
-Estimated Peak Memory Range: 0.59-51.28 MB
-Compute Units: NPU (124) | Total (124)
-
-
-```
 ## How does this work?
 
 This [export script](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/WideResNet50/export.py)