Upload README.md with huggingface_hub

README.md

@@ -33,7 +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 | 8.729 ms | 7 - 10 MB | FP16 | NPU |  [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 8.636 ms | 8 - 25 MB | FP16 | NPU |  [FastSam-S.tflite](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 8.361 ms | 5 - 19 MB | FP16 | NPU |  [FastSam-S.so](https://huggingface.co/qualcomm/FastSam-S/blob/main/FastSam-S.so) 
 
 
 ## Installation
@@ -94,10 +95,10 @@ python -m qai_hub_models.models.fastsam_s.export
 ```
 Profile Job summary of FastSam-S
 --------------------------------------------------
-Device: QCS8550 (Proxy) (12)
-Estimated Inference Time: 8.74 ms
-Estimated Peak Memory Range: 7.44-24.17 MB
-Compute Units: NPU (288) | Total (288)
+Device: Snapdragon X Elite CRD (11)
+Estimated Inference Time: 9.18 ms
+Estimated Peak Memory Range: 4.71-4.71 MB
+Compute Units: NPU (286) | Total (286)
 
 
 ```