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 | 25.516 ms | 3 - 5 MB | FP16 | NPU |  [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 20.433 ms | 24 - 48 MB | FP16 | NPU |  [FFNet-54S.so](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 25.024 ms | 2 - 5 MB | FP16 | NPU |  [FFNet-54S.tflite](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 19.758 ms | 24 - 46 MB | FP16 | NPU |  [FFNet-54S.so](https://huggingface.co/qualcomm/FFNet-54S/blob/main/FFNet-54S.so) 
 
 
 ## Installation
@@ -93,23 +93,6 @@ device. This script does the following:
 python -m qai_hub_models.models.ffnet_54s.export
 ```
 
-```
-Profile Job summary of FFNet-54S
---------------------------------------------------
-Device: Samsung Galaxy S24 (14)
-Estimated Inference Time: 18.56 ms
-Estimated Peak Memory Range: 2.14-116.64 MB
-Compute Units: NPU (113) | Total (113)
-
-Profile Job summary of FFNet-54S
---------------------------------------------------
-Device: Samsung Galaxy S24 (14)
-Estimated Inference Time: 14.52 ms
-Estimated Peak Memory Range: 220.72-287.16 MB
-Compute Units: NPU (175) | Total (175)
-
-
-```
 ## How does this work?
 
 This [export script](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/FFNet-54S/export.py)