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 | 41.432 ms | 21 - 24 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 | 42.249 ms | 3 - 20 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 | 42.095 ms | 21 - 24 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 | 42.393 ms | 3 - 20 MB | FP16 | NPU |  [FCN-ResNet50.so](https://huggingface.co/qualcomm/FCN-ResNet50/blob/main/FCN-ResNet50.so) 
 
 
 
@@ -99,7 +99,7 @@ python -m qai_hub_models.models.fcn_resnet50.export
 Profile Job summary of FCN-ResNet50
 --------------------------------------------------
 Device: Snapdragon X Elite CRD (11)
-Estimated Inference Time: 70.34 ms
+Estimated Inference Time: 39.51 ms
 Estimated Peak Memory Range: 3.01-3.01 MB
 Compute Units: NPU (127) | Total (127)
 
@@ -126,7 +126,6 @@ from qai_hub_models.models.fcn_resnet50 import Model
 
 # Load the model
 torch_model = Model.from_pretrained()
-torch_model.eval()
 
 # Device
 device = hub.Device("Samsung Galaxy S23")