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 | 7.101 ms | 1 - 2 MB | INT8 | NPU |  [FFNet-54S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-54S-Quantized/blob/main/FFNet-54S-Quantized.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 4.974 ms | 6 - 19 MB | INT8 | NPU |  [FFNet-54S-Quantized.so](https://huggingface.co/qualcomm/FFNet-54S-Quantized/blob/main/FFNet-54S-Quantized.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 7.12 ms | 2 - 10 MB | INT8 | NPU |  [FFNet-54S-Quantized.tflite](https://huggingface.co/qualcomm/FFNet-54S-Quantized/blob/main/FFNet-54S-Quantized.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 4.948 ms | 6 - 16 MB | INT8 | NPU |  [FFNet-54S-Quantized.so](https://huggingface.co/qualcomm/FFNet-54S-Quantized/blob/main/FFNet-54S-Quantized.so) 
 
 
 ## Installation
@@ -99,7 +99,7 @@ python -m qai_hub_models.models.ffnet_54s_quantized.export
 Profile Job summary of FFNet-54S-Quantized
 --------------------------------------------------
 Device: Snapdragon X Elite CRD (11)
-Estimated Inference Time: 6.01 ms
+Estimated Inference Time: 5.96 ms
 Estimated Peak Memory Range: 6.01-6.01 MB
 Compute Units: NPU (110) | Total (110)