Upload README.md with huggingface_hub

README.md

@@ -11,7 +11,7 @@ tags:
 
 ---
 
-![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_small/web-assets/banner.png)
+![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_small/web-assets/model_demo.png)
 
 # Swin-Small: Optimized for Mobile Deployment
 ## Imagenet classifier and general purpose backbone
@@ -36,7 +36,7 @@ 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 | 52.492 ms | 0 - 212 MB | FP16 | GPU |  [Swin-Small.tflite](https://huggingface.co/qualcomm/Swin-Small/blob/main/Swin-Small.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 51.094 ms | 0 - 3 MB | FP16 | NPU |  [Swin-Small.tflite](https://huggingface.co/qualcomm/Swin-Small/blob/main/Swin-Small.tflite) 
 
 
 ## Installation
@@ -97,9 +97,9 @@ python -m qai_hub_models.models.swin_small.export
 Profile Job summary of Swin-Small
 --------------------------------------------------
 Device: Samsung Galaxy S23 Ultra (13)
-Estimated Inference Time: 52.49 ms
-Estimated Peak Memory Range: 0.01-211.72 MB
-Compute Units: GPU (1965) | Total (1965)
+Estimated Inference Time: 51.09 ms
+Estimated Peak Memory Range: 0.11-3.18 MB
+Compute Units: NPU (1965) | Total (1965)
 
 
 ```
@@ -179,7 +179,7 @@ With the output of the model, you can compute like PSNR, relative errors or
 spot check the output with expected output.
 
 **Note**: This on-device profiling and inference requires access to Qualcomm®
-AI Hub. [Sign up for early access](https://aihub.qualcomm.com/sign-up).
+AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
 
 
 ## Run demo on a cloud-hosted device