Upload README.md with huggingface_hub

README.md

@@ -37,8 +37,8 @@ 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 | 23.193 ms | 2 - 4 MB | FP16 | NPU |  [FFNet-40S.tflite](https://huggingface.co/qualcomm/FFNet-40S/blob/main/FFNet-40S.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 17.411 ms | 24 - 43 MB | FP16 | NPU |  [FFNet-40S.so](https://huggingface.co/qualcomm/FFNet-40S/blob/main/FFNet-40S.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 16.96 ms | 2 - 4 MB | FP16 | NPU |  [FFNet-40S.tflite](https://huggingface.co/qualcomm/FFNet-40S/blob/main/FFNet-40S.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 17.413 ms | 24 - 44 MB | FP16 | NPU |  [FFNet-40S.so](https://huggingface.co/qualcomm/FFNet-40S/blob/main/FFNet-40S.so) 
 
 
 
@@ -101,7 +101,7 @@ python -m qai_hub_models.models.ffnet_40s.export
 Profile Job summary of FFNet-40S
 --------------------------------------------------
 Device: Snapdragon X Elite CRD (11)
-Estimated Inference Time: 23.36 ms
+Estimated Inference Time: 17.74 ms
 Estimated Peak Memory Range: 24.05-24.05 MB
 Compute Units: NPU (140) | Total (140)
 
@@ -128,7 +128,6 @@ from qai_hub_models.models.ffnet_40s import Model
 
 # Load the model
 torch_model = Model.from_pretrained()
-torch_model.eval()
 
 # Device
 device = hub.Device("Samsung Galaxy S23")