Upload README.md with huggingface_hub

README.md

@@ -34,8 +34,8 @@ 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 | 72.165 ms | 3 - 6 MB | FP16 | NPU |  [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 67.072 ms | 0 - 99 MB | FP16 | NPU |  [ESRGAN.so](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 63.878 ms | 3 - 6 MB | FP16 | NPU |  [ESRGAN.tflite](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 64.833 ms | 0 - 100 MB | FP16 | NPU |  [ESRGAN.so](https://huggingface.co/qualcomm/ESRGAN/blob/main/ESRGAN.so) 
 
 
 
@@ -96,9 +96,9 @@ python -m qai_hub_models.models.esrgan.export
 ```
 Profile Job summary of ESRGAN
 --------------------------------------------------
-Device: SA8255 (Proxy) (13)
-Estimated Inference Time: 67.76 ms
-Estimated Peak Memory Range: 0.09-98.13 MB
+Device: Snapdragon X Elite CRD (11)
+Estimated Inference Time: 65.37 ms
+Estimated Peak Memory Range: 0.21-0.21 MB
 Compute Units: NPU (1026) | Total (1026)
 
 
@@ -184,6 +184,20 @@ AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
 
 
 
+## Run demo on a cloud-hosted device
+
+You can also run the demo on-device.
+
+```bash
+python -m qai_hub_models.models.esrgan.demo --on-device
+```
+
+**NOTE**: If you want running in a Jupyter Notebook or Google Colab like
+environment, please add the following to your cell (instead of the above).
+```
+%run -m qai_hub_models.models.esrgan.demo -- --on-device
+```
+
 
 ## Deploying compiled model to Android