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 | 12.935 ms | 0 - 7 MB | FP16 | NPU |  [Yolo-NAS.tflite](https://huggingface.co/qualcomm/Yolo-NAS/blob/main/Yolo-NAS.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 14.574 ms | 6 - 20 MB | FP16 | NPU |  [Yolo-NAS.so](https://huggingface.co/qualcomm/Yolo-NAS/blob/main/Yolo-NAS.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 10.996 ms | 0 - 4 MB | FP16 | NPU |  [Yolo-NAS.tflite](https://huggingface.co/qualcomm/Yolo-NAS/blob/main/Yolo-NAS.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 14.669 ms | 5 - 23 MB | FP16 | NPU |  [Yolo-NAS.so](https://huggingface.co/qualcomm/Yolo-NAS/blob/main/Yolo-NAS.so) 
 
 
 
@@ -101,8 +101,8 @@ python -m qai_hub_models.models.yolonas.export
 Profile Job summary of Yolo-NAS
 --------------------------------------------------
 Device: Snapdragon X Elite CRD (11)
-Estimated Inference Time: 11.90 ms
-Estimated Peak Memory Range: 4.59-4.59 MB
+Estimated Inference Time: 10.61 ms
+Estimated Peak Memory Range: 4.70-4.70 MB
 Compute Units: NPU (289) | Total (289)
 
 
@@ -128,7 +128,6 @@ from qai_hub_models.models.yolonas import Model
 
 # Load the model
 torch_model = Model.from_pretrained()
-torch_model.eval()
 
 # Device
 device = hub.Device("Samsung Galaxy S23")