Upload README.md with huggingface_hub

README.md

@@ -36,30 +36,26 @@ More details on model performance across various devices, can be found
 
 | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
 |---|---|---|---|---|---|---|---|---|
-| VITQuantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 5.248 ms | 0 - 184 MB | INT8 | NPU | [VITQuantized.so](https://huggingface.co/qualcomm/VITQuantized/blob/main/VITQuantized.so) |
-| VITQuantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 39.154 ms | 0 - 155 MB | INT8 | NPU | [VITQuantized.onnx](https://huggingface.co/qualcomm/VITQuantized/blob/main/VITQuantized.onnx) |
-| VITQuantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 3.522 ms | 0 - 45 MB | INT8 | NPU | [VITQuantized.so](https://huggingface.co/qualcomm/VITQuantized/blob/main/VITQuantized.so) |
-| VITQuantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 31.231 ms | 0 - 82 MB | INT8 | NPU | [VITQuantized.onnx](https://huggingface.co/qualcomm/VITQuantized/blob/main/VITQuantized.onnx) |
-| VITQuantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 3.255 ms | 0 - 63 MB | INT8 | NPU | Use Export Script |
-| VITQuantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 33.006 ms | 0 - 83 MB | INT8 | NPU | [VITQuantized.onnx](https://huggingface.co/qualcomm/VITQuantized/blob/main/VITQuantized.onnx) |
-| VITQuantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 21.663 ms | 0 - 12 MB | INT8 | NPU | Use Export Script |
-| VITQuantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 4.73 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
-| VITQuantized | SA7255P ADP | SA7255P | QNN | 38.812 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
-| VITQuantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 4.742 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
-| VITQuantized | SA8295P ADP | SA8295P | QNN | 6.827 ms | 0 - 15 MB | INT8 | NPU | Use Export Script |
-| VITQuantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 4.735 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
+| VITQuantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 5.254 ms | 0 - 214 MB | INT8 | NPU | [VITQuantized.so](https://huggingface.co/qualcomm/VITQuantized/blob/main/VITQuantized.so) |
+| VITQuantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 3.527 ms | 0 - 43 MB | INT8 | NPU | [VITQuantized.so](https://huggingface.co/qualcomm/VITQuantized/blob/main/VITQuantized.so) |
+| VITQuantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 3.258 ms | 0 - 66 MB | INT8 | NPU | Use Export Script |
+| VITQuantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 21.821 ms | 0 - 12 MB | INT8 | NPU | Use Export Script |
+| VITQuantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 4.766 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
+| VITQuantized | SA7255P ADP | SA7255P | QNN | 38.733 ms | 1 - 10 MB | INT8 | NPU | Use Export Script |
+| VITQuantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 4.748 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
+| VITQuantized | SA8295P ADP | SA8295P | QNN | 7.211 ms | 0 - 15 MB | INT8 | NPU | Use Export Script |
+| VITQuantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 4.758 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
 | VITQuantized | SA8775P ADP | SA8775P | QNN | 6.256 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
-| VITQuantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 5.956 ms | 0 - 46 MB | INT8 | NPU | Use Export Script |
-| VITQuantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 5.154 ms | 0 - 0 MB | INT8 | NPU | Use Export Script |
-| VITQuantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 51.116 ms | 87 - 87 MB | INT8 | NPU | [VITQuantized.onnx](https://huggingface.co/qualcomm/VITQuantized/blob/main/VITQuantized.onnx) |
+| VITQuantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 6.068 ms | 0 - 49 MB | INT8 | NPU | Use Export Script |
+| VITQuantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 5.133 ms | 0 - 0 MB | INT8 | NPU | Use Export Script |
 
 
 
 
 ## Installation
 
-This model can be installed as a Python package via pip.
 
+Install the package via pip:
 ```bash
 pip install qai-hub-models
 ```
@@ -115,8 +111,8 @@ Profiling Results
 VITQuantized
 Device                          : Samsung Galaxy S23 (13)
 Runtime                         : QNN                    
-Estimated inference time (ms)   : 5.2                    
-Estimated peak memory usage (MB): [0, 184]               
+Estimated inference time (ms)   : 5.3                    
+Estimated peak memory usage (MB): [0, 214]               
 Total # Ops                     : 903                    
 Compute Unit(s)                 : NPU (903 ops)          
 ```
@@ -143,7 +139,7 @@ from qai_hub_models.models.vit_quantized import Model
 torch_model = Model.from_pretrained()
 
 # Device
-device = hub.Device("Samsung Galaxy S23")
+device = hub.Device("Samsung Galaxy S24")
 
 # Trace model
 input_shape = torch_model.get_input_spec()
@@ -235,7 +231,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 
 
 ## License
-* The license for the original implementation of VITQuantized can be found [here](https://github.com/pytorch/vision/blob/main/LICENSE).
+* The license for the original implementation of VITQuantized 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)