Upload README.md with huggingface_hub

README.md

@@ -33,8 +33,8 @@ 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 | 7.953 ms | 2 - 5 MB | FP16 | NPU |  [Yolo-v6.tflite](https://huggingface.co/qualcomm/Yolo-v6/blob/main/Yolo-v6.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 6.885 ms | 5 - 18 MB | FP16 | NPU |  [Yolo-v6.so](https://huggingface.co/qualcomm/Yolo-v6/blob/main/Yolo-v6.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 7.322 ms | 0 - 2 MB | FP16 | NPU |  [Yolo-v6.tflite](https://huggingface.co/qualcomm/Yolo-v6/blob/main/Yolo-v6.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 5.353 ms | 5 - 15 MB | FP16 | NPU |  [Yolo-v6.so](https://huggingface.co/qualcomm/Yolo-v6/blob/main/Yolo-v6.so) 
 
 
 ## Installation
@@ -94,17 +94,10 @@ python -m qai_hub_models.models.yolov6.export
 ```
 Profile Job summary of Yolo-v6
 --------------------------------------------------
-Device: QCS8550 (Proxy) (12)
-Estimated Inference Time: 7.95 ms
-Estimated Peak Memory Range: 0.21-3.29 MB
-Compute Units: NPU (182) | Total (182)
-
-Profile Job summary of Yolo-v6
---------------------------------------------------
-Device: QCS8550 (Proxy) (12)
-Estimated Inference Time: 6.88 ms
-Estimated Peak Memory Range: 4.72-18.45 MB
-Compute Units: NPU (229) | Total (229)
+Device: Snapdragon X Elite CRD (11)
+Estimated Inference Time: 6.75 ms
+Estimated Peak Memory Range: 4.70-4.70 MB
+Compute Units: NPU (228) | Total (228)
 
 
 ```