Upload README.md with huggingface_hub

README.md

@@ -32,8 +32,8 @@ 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 | 57.759 ms | 0 - 163 MB | FP16 | GPU |  [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 146.022 ms | 1 - 9 MB | FP16 | GPU |  [DeepLabV3-ResNet50.so](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 57.559 ms | 0 - 3 MB | FP16 | GPU |  [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 145.372 ms | 1 - 16 MB | FP16 | GPU |  [DeepLabV3-ResNet50.so](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.so) 
 
 
 ## Installation
@@ -93,16 +93,16 @@ python -m qai_hub_models.models.deeplabv3_resnet50.export
 ```
 Profile Job summary of DeepLabV3-ResNet50
 --------------------------------------------------
-Device: Samsung Galaxy S23 Ultra (13)
-Estimated Inference Time: 57.76 ms
-Estimated Peak Memory Range: 0.01-163.42 MB
+Device: Samsung Galaxy S24 (14)
+Estimated Inference Time: 40.15 ms
+Estimated Peak Memory Range: 4.16-27.88 MB
 Compute Units: GPU (96) | Total (96)
 
 Profile Job summary of DeepLabV3-ResNet50
 --------------------------------------------------
-Device: Samsung Galaxy S23 Ultra (13)
-Estimated Inference Time: 146.02 ms
-Estimated Peak Memory Range: 0.77-9.09 MB
+Device: Samsung Galaxy S24 (14)
+Estimated Inference Time: 104.46 ms
+Estimated Peak Memory Range: 0.64-23.38 MB
 Compute Units: GPU (82) | Total (82)
 
 
@@ -208,7 +208,7 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 ## License
 - The license for the original implementation of DeepLabV3-ResNet50 can be found
   [here](https://github.com/pytorch/vision/blob/main/LICENSE).
-- The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf).
+- The license for the compiled assets for on-device deployment can be found [here]({deploy_license_url})
 
 ## References
 * [Rethinking Atrous Convolution for Semantic Image Segmentation](https://arxiv.org/abs/1706.05587)