Upload README.md with huggingface_hub

README.md

@@ -18,7 +18,7 @@ tags:
 
 ConvNextTiny is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.
 
-This model is an implementation of ConvNext-Tiny-w8a16-Quantized found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/convnext.py).
+This model is an implementation of ConvNext-Tiny-w8a16-Quantized found [here]({source_repo}).
 This repository provides scripts to run ConvNext-Tiny-w8a16-Quantized on Qualcomm® devices.
 More details on model performance across various devices, can be found
 [here](https://aihub.qualcomm.com/models/convnext_tiny_w8a16_quantized).
@@ -34,14 +34,21 @@ More details on model performance across various devices, can be found
   - Model size: 28 MB
   - Precision: w8a16 (8-bit weights, 16-bit activations)
 
+| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
+|---|---|---|---|---|---|---|---|---|
+| ConvNext-Tiny-w8a16-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 3.622 ms | 0 - 116 MB | INT8 | NPU | [ConvNext-Tiny-w8a16-Quantized.so](https://huggingface.co/qualcomm/ConvNext-Tiny-w8a16-Quantized/blob/main/ConvNext-Tiny-w8a16-Quantized.so) |
+| ConvNext-Tiny-w8a16-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 2.61 ms | 0 - 35 MB | INT8 | NPU | [ConvNext-Tiny-w8a16-Quantized.so](https://huggingface.co/qualcomm/ConvNext-Tiny-w8a16-Quantized/blob/main/ConvNext-Tiny-w8a16-Quantized.so) |
+| ConvNext-Tiny-w8a16-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 13.298 ms | 0 - 8 MB | INT8 | NPU | Use Export Script |
+| ConvNext-Tiny-w8a16-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 3.178 ms | 0 - 1 MB | INT8 | NPU | Use Export Script |
+| ConvNext-Tiny-w8a16-Quantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 3.204 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
+| ConvNext-Tiny-w8a16-Quantized | SA8775 (Proxy) | SA8775P Proxy | QNN | 3.204 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
+| ConvNext-Tiny-w8a16-Quantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 3.198 ms | 0 - 1 MB | INT8 | NPU | Use Export Script |
+| ConvNext-Tiny-w8a16-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 4.241 ms | 0 - 41 MB | INT8 | NPU | Use Export Script |
+| ConvNext-Tiny-w8a16-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 2.406 ms | 0 - 35 MB | INT8 | NPU | Use Export Script |
+| ConvNext-Tiny-w8a16-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 3.505 ms | 0 - 0 MB | INT8 | NPU | Use Export Script |
 
 
 
-| 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 | QNN Model Library | 3.447 ms | 0 - 12 MB | INT8 | NPU |  [ConvNext-Tiny-w8a16-Quantized.so](https://huggingface.co/qualcomm/ConvNext-Tiny-w8a16-Quantized/blob/main/ConvNext-Tiny-w8a16-Quantized.so) 
-
-
 
 ## Installation
 
@@ -97,16 +104,16 @@ device. This script does the following:
 ```bash
 python -m qai_hub_models.models.convnext_tiny_w8a16_quantized.export
 ```
-
 ```
-Profile Job summary of ConvNext-Tiny-w8a16-Quantized
---------------------------------------------------
-Device: Snapdragon X Elite CRD (11)
-Estimated Inference Time: 3.35 ms
-Estimated Peak Memory Range: 0.29-0.29 MB
-Compute Units: NPU (215) | Total (215)
-
-
+Profiling Results
+------------------------------------------------------------
+ConvNext-Tiny-w8a16-Quantized
+Device                          : Samsung Galaxy S23 (13)
+Runtime                         : QNN                    
+Estimated inference time (ms)   : 3.6                    
+Estimated peak memory usage (MB): [0, 116]               
+Total # Ops                     : 215                    
+Compute Unit(s)                 : NPU (215 ops)          
 ```
 
 
@@ -145,15 +152,19 @@ provides instructions on how to use the `.so` shared library  in an Android appl
 Get more details on ConvNext-Tiny-w8a16-Quantized's performance across various devices [here](https://aihub.qualcomm.com/models/convnext_tiny_w8a16_quantized).
 Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 
+
 ## License
-- The license for the original implementation of ConvNext-Tiny-w8a16-Quantized 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 original implementation of ConvNext-Tiny-w8a16-Quantized 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)
+
+
 
 ## References
 * [A ConvNet for the 2020s](https://arxiv.org/abs/2201.03545)
 * [Source Model Implementation](https://github.com/pytorch/vision/blob/main/torchvision/models/convnext.py)
 
+
+
 ## Community
 * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
 * For questions or feedback please [reach out to us](mailto:[email protected]).