Upload README.md with huggingface_hub

README.md

@@ -34,7 +34,7 @@ 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 | 53.317 ms | 0 - 8 MB | FP16 | NPU |  [DETR-ResNet101.tflite](https://huggingface.co/qualcomm/DETR-ResNet101/blob/main/DETR-ResNet101.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 47.978 ms | 0 - 9 MB | FP16 | NPU |  [DETR-ResNet101.tflite](https://huggingface.co/qualcomm/DETR-ResNet101/blob/main/DETR-ResNet101.tflite) 
 
 
 ## Installation
@@ -92,16 +92,6 @@ device. This script does the following:
 python -m qai_hub_models.models.detr_resnet101.export
 ```
 
-```
-Profile Job summary of DETR-ResNet101
---------------------------------------------------
-Device: Samsung Galaxy S24 (14)
-Estimated Inference Time: 39.54 ms
-Estimated Peak Memory Range: 1.35-251.40 MB
-Compute Units: NPU (954),GPU (2),CPU (1) | Total (957)
-
-
-```
 ## How does this work?
 
 This [export script](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/DETR-ResNet101/export.py)