Upload README.md with huggingface_hub

README.md

@@ -38,10 +38,10 @@ 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 | 11.011 ms | 0 - 3 MB | FP16 | NPU |  [CLIPTextEncoder.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPTextEncoder.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 66.007 ms | 0 - 3 MB | FP16 | NPU |  [CLIPImageEncoder.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPImageEncoder.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 7.838 ms | 0 - 18 MB | FP16 | NPU |  [CLIPTextEncoder.so](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPTextEncoder.so) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 50.689 ms | 0 - 60 MB | FP16 | NPU |  [CLIPImageEncoder.so](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPImageEncoder.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 11.739 ms | 0 - 8 MB | FP16 | NPU |  [CLIPTextEncoder.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPTextEncoder.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 65.346 ms | 0 - 9 MB | FP16 | NPU |  [CLIPImageEncoder.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPImageEncoder.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 7.795 ms | 0 - 16 MB | FP16 | NPU |  [CLIPTextEncoder.so](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPTextEncoder.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 50.085 ms | 0 - 61 MB | FP16 | NPU |  [CLIPImageEncoder.so](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/CLIPImageEncoder.so) 
 
 
 
@@ -103,17 +103,17 @@ python -m qai_hub_models.models.openai_clip.export
 ```
 Profile Job summary of CLIPTextEncoder
 --------------------------------------------------
-Device: SA8255 (Proxy) (13)
-Estimated Inference Time: 7.79 ms
-Estimated Peak Memory Range: 0.00-20.18 MB
+Device: Snapdragon X Elite CRD (11)
+Estimated Inference Time: 8.29 ms
+Estimated Peak Memory Range: 0.16-0.16 MB
 Compute Units: NPU (377) | Total (377)
 
 Profile Job summary of CLIPImageEncoder
 --------------------------------------------------
-Device: SA8255 (Proxy) (13)
-Estimated Inference Time: 50.36 ms
-Estimated Peak Memory Range: 0.08-50.08 MB
-Compute Units: NPU (371) | Total (371)
+Device: Snapdragon X Elite CRD (11)
+Estimated Inference Time: 36.01 ms
+Estimated Peak Memory Range: 0.57-0.57 MB
+Compute Units: NPU (369) | Total (369)
 
 
 ```
@@ -134,29 +134,49 @@ 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.openai_clip import Model
+from qai_hub_models.models.openai_clip import CLIPTextEncoder,CLIPImageEncoder
 
 # Load the model
-torch_model = Model.from_pretrained()
+text_encoder_model = CLIPTextEncoder.from_pretrained()
+
+image_encoder_model = CLIPImageEncoder.from_pretrained()
+
 
 # Device
 device = hub.Device("Samsung Galaxy S23")
 
+
 # Trace model
-input_shape = torch_model.get_input_spec()
-sample_inputs = torch_model.sample_inputs()
+text_encoder_input_shape = text_encoder_model.get_input_spec()
+text_encoder_sample_inputs = text_encoder_model.sample_inputs()
 
-pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])
+traced_text_encoder_model = torch.jit.trace(text_encoder_model, [torch.tensor(data[0]) for _, data in text_encoder_sample_inputs.items()])
 
 # Compile model on a specific device
-compile_job = hub.submit_compile_job(
-    model=pt_model,
+text_encoder_compile_job = hub.submit_compile_job(
+    model=traced_text_encoder_model ,
     device=device,
-    input_specs=torch_model.get_input_spec(),
+    input_specs=text_encoder_model.get_input_spec(),
 )
 
 # Get target model to run on-device
-target_model = compile_job.get_target_model()
+text_encoder_target_model = text_encoder_compile_job.get_target_model()
+
+# Trace model
+image_encoder_input_shape = image_encoder_model.get_input_spec()
+image_encoder_sample_inputs = image_encoder_model.sample_inputs()
+
+traced_image_encoder_model = torch.jit.trace(image_encoder_model, [torch.tensor(data[0]) for _, data in image_encoder_sample_inputs.items()])
+
+# Compile model on a specific device
+image_encoder_compile_job = hub.submit_compile_job(
+    model=traced_image_encoder_model ,
+    device=device,
+    input_specs=image_encoder_model.get_input_spec(),
+)
+
+# Get target model to run on-device
+image_encoder_target_model = image_encoder_compile_job.get_target_model()
 
 ```
 
@@ -168,10 +188,16 @@ After compiling models from step 1. Models can be profiled model on-device using
 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,
-)
+
+text_encoder_profile_job = hub.submit_profile_job(
+        model=text_encoder_target_model,
+        device=device,
+        )       
+
+image_encoder_profile_job = hub.submit_profile_job(
+        model=image_encoder_target_model,
+        device=device,
+        )       
 
 ```
 
@@ -180,14 +206,20 @@ Step 3: **Verify on-device accuracy**
 To verify the accuracy of the model on-device, you can run on-device inference
 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()
+text_encoder_input_data = text_encoder_model.sample_inputs()
+text_encoder_inference_job = hub.submit_inference_job(
+        model=text_encoder_target_model,
+        device=device,
+        inputs=text_encoder_input_data,
+    )
+text_encoder_inference_job.download_output_data()
+image_encoder_input_data = image_encoder_model.sample_inputs()
+image_encoder_inference_job = hub.submit_inference_job(
+        model=image_encoder_target_model,
+        device=device,
+        inputs=image_encoder_input_data,
+    )
+image_encoder_inference_job.download_output_data()
 
 ```
 With the output of the model, you can compute like PSNR, relative errors or