Upload README.md with huggingface_hub

README.md

@@ -38,8 +38,8 @@ 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 | 28.867 ms | 0 - 6 MB | FP16 | NPU |  [Swin-Small.tflite](https://huggingface.co/qualcomm/Swin-Small/blob/main/Swin-Small.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 23.696 ms | 0 - 35 MB | FP16 | NPU |  [Swin-Small.so](https://huggingface.co/qualcomm/Swin-Small/blob/main/Swin-Small.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 64.033 ms | 7 - 14 MB | FP16 | NPU |  [Swin-Small.tflite](https://huggingface.co/qualcomm/Swin-Small/blob/main/Swin-Small.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 23.891 ms | 0 - 42 MB | FP16 | NPU |  [Swin-Small.so](https://huggingface.co/qualcomm/Swin-Small/blob/main/Swin-Small.so) 
 
 
 
@@ -100,9 +100,9 @@ python -m qai_hub_models.models.swin_small.export
 ```
 Profile Job summary of Swin-Small
 --------------------------------------------------
-Device: SA8255 (Proxy) (13)
-Estimated Inference Time: 23.40 ms
-Estimated Peak Memory Range: 0.04-38.23 MB
+Device: Snapdragon X Elite CRD (11)
+Estimated Inference Time: 22.25 ms
+Estimated Peak Memory Range: 0.57-0.57 MB
 Compute Units: NPU (1246) | Total (1246)
 
 
@@ -124,29 +124,13 @@ in memory using the `jit.trace` and then call the `submit_compile_job` API.
 import torch
 
 import qai_hub as hub
-from qai_hub_models.models.swin_small import Model
+from qai_hub_models.models.swin_small import 
 
 # Load the model
-torch_model = Model.from_pretrained()
 
 # Device
 device = hub.Device("Samsung Galaxy S23")
 
-# Trace model
-input_shape = torch_model.get_input_spec()
-sample_inputs = torch_model.sample_inputs()
-
-pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])
-
-# Compile model on a specific device
-compile_job = hub.submit_compile_job(
-    model=pt_model,
-    device=device,
-    input_specs=torch_model.get_input_spec(),
-)
-
-# Get target model to run on-device
-target_model = compile_job.get_target_model()
 
 ```
 
@@ -159,10 +143,10 @@ provisioned in the cloud.  Once the job is submitted, you can navigate to a
 provided job URL to view a variety of on-device performance metrics.
 ```python
 profile_job = hub.submit_profile_job(
-    model=target_model,
-    device=device,
-)
-
+        model=target_model,
+        device=device,
+        )
+        
 ```
 
 Step 3: **Verify on-device accuracy**
@@ -172,12 +156,11 @@ on sample input data on the same cloud hosted device.
 ```python
 input_data = torch_model.sample_inputs()
 inference_job = hub.submit_inference_job(
-    model=target_model,
-    device=device,
-    inputs=input_data,
-)
-
-on_device_output = inference_job.download_output_data()
+        model=target_model,
+        device=device,
+        inputs=input_data,
+    )
+    on_device_output = inference_job.download_output_data()
 
 ```
 With the output of the model, you can compute like PSNR, relative errors or