v0.19.1

See https://github.com/quic/ai-hub-models/releases/v0.19.1 for changelog.

Signed-off-by: QAIHM Team <[email protected]>

qai_hub_models/models/aotgan/README.md

@@ -5,7 +5,7 @@
 
 AOT-GAN is a machine learning model that allows to erase and in-paint part of given input image.
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of AOT-GAN found [here](https://github.com/researchmm/AOT-GAN-for-Inpainting). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/aotgan).
 

qai_hub_models/models/baichuan2_7b_quantized/README.md

@@ -5,7 +5,7 @@
 
 Baichuan2-7B is a family of LLMs. It achieves the state-of-the-art performance of its size on standard Chinese and English authoritative benchmarks (C-EVAL/MMLU). 4-bit weights and 16-bit activations making it suitable for on-device deployment. For Prompt and output length specified below, the time to first token is Baichuan2-PromptProcessor-Quantized's latency and average time per addition token is Baichuan2-TokenGenerator-Quantized's latency.
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of Baichuan2-7B found [here](https://github.com/baichuan-inc/Baichuan-7B/). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/baichuan2_7b_quantized).
 

qai_hub_models/models/beit/README.md

@@ -5,7 +5,7 @@
 
 Beit 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.
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of Beit found [here](https://github.com/microsoft/unilm/tree/master/beit). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/beit).
 

qai_hub_models/models/conditional_detr_resnet50/README.md

@@ -5,7 +5,7 @@
 
 DETR is a machine learning model that can detect objects (trained on COCO dataset).
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of Conditional-DETR-ResNet50 found [here](https://github.com/huggingface/transformers/tree/main/src/transformers/models/conditional_detr). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/conditional_detr_resnet50).
 

qai_hub_models/models/controlnet_quantized/README.md

@@ -5,7 +5,7 @@
 
 On-device, high-resolution image synthesis from text and image prompts. ControlNet guides Stable-diffusion with provided input image to generate accurate images from given input prompt.
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of ControlNet found [here](https://github.com/lllyasviel/ControlNet). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/controlnet_quantized).
 

qai_hub_models/models/convnext_base/README.md

@@ -5,7 +5,7 @@
 
 ConvNextBase 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.
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of ConvNext-Base found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/convnext.py). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/convnext_base).
 

qai_hub_models/models/convnext_tiny/README.md

@@ -5,7 +5,7 @@
 
 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.
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of ConvNext-Tiny found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/convnext.py). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/convnext_tiny).
 

qai_hub_models/models/convnext_tiny_w8a16_quantized/README.md

@@ -5,7 +5,7 @@
 
 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.
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of ConvNext-Tiny-w8a16-Quantized found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/convnext.py). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/convnext_tiny_w8a16_quantized).
 

qai_hub_models/models/convnext_tiny_w8a8_quantized/README.md

@@ -5,7 +5,7 @@
 
 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.
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of ConvNext-Tiny-w8a8-Quantized found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/convnext.py). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/convnext_tiny_w8a8_quantized).
 

qai_hub_models/models/ddrnet23_slim/README.md

@@ -5,7 +5,7 @@
 
 DDRNet23Slim is a machine learning model that segments an image into semantic classes, specifically designed for road-based scenes. It is designed for the application of self-driving cars.
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of DDRNet23-Slim found [here](https://github.com/chenjun2hao/DDRNet.pytorch). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/ddrnet23_slim).
 

qai_hub_models/models/deeplabv3_plus_mobilenet/README.md

@@ -5,7 +5,7 @@
 
 DeepLabV3 is designed for semantic segmentation at multiple scales, trained on the various datasets. It uses MobileNet as a backbone.
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of DeepLabV3-Plus-MobileNet found [here](https://github.com/jfzhang95/pytorch-deeplab-xception). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/deeplabv3_plus_mobilenet).
 

qai_hub_models/models/deeplabv3_plus_mobilenet_quantized/README.md

@@ -5,7 +5,7 @@
 
 DeepLabV3 Quantized is designed for semantic segmentation at multiple scales, trained on various datasets. It uses MobileNet as a backbone.
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of DeepLabV3-Plus-MobileNet-Quantized found [here](https://github.com/jfzhang95/pytorch-deeplab-xception). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/deeplabv3_plus_mobilenet_quantized).
 

qai_hub_models/models/deeplabv3_resnet50/README.md

@@ -5,7 +5,7 @@
 
 DeepLabV3 is designed for semantic segmentation at multiple scales, trained on the COCO dataset. It uses ResNet50 as a backbone.
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of DeepLabV3-ResNet50 found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/segmentation/deeplabv3.py). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/deeplabv3_resnet50).
 

qai_hub_models/models/densenet121/README.md

@@ -5,7 +5,7 @@
 
 Densenet 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.
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of DenseNet-121 found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/densenet.py). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/densenet121).
 

qai_hub_models/models/densenet121_quantized/README.md

@@ -5,7 +5,7 @@
 
 Densenet 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.
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of DenseNet-121-Quantized found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/densenet.py). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/densenet121_quantized).
 

qai_hub_models/models/detr_resnet101/README.md

@@ -5,7 +5,7 @@
 
 DETR is a machine learning model that can detect objects (trained on COCO dataset).
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of DETR-ResNet101 found [here](https://github.com/facebookresearch/detr). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/detr_resnet101).
 

qai_hub_models/models/detr_resnet101_dc5/README.md

@@ -5,7 +5,7 @@
 
 DETR is a machine learning model that can detect objects (trained on COCO dataset).
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of DETR-ResNet101-DC5 found [here](https://github.com/facebookresearch/detr). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/detr_resnet101_dc5).
 

qai_hub_models/models/detr_resnet50/README.md

@@ -5,7 +5,7 @@
 
 DETR is a machine learning model that can detect objects (trained on COCO dataset).
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of DETR-ResNet50 found [here](https://github.com/facebookresearch/detr). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/detr_resnet50).
 

qai_hub_models/models/detr_resnet50_dc5/README.md

@@ -5,7 +5,7 @@
 
 DETR is a machine learning model that can detect objects (trained on COCO dataset).
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of DETR-ResNet50-DC5 found [here](https://github.com/facebookresearch/detr). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/detr_resnet50_dc5).
 

qai_hub_models/models/efficientnet_b0/README.md

@@ -5,7 +5,7 @@
 
 EfficientNetB0 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.
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of EfficientNet-B0 found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/efficientnet.py). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/efficientnet_b0).
 

qai_hub_models/models/efficientnet_b4/README.md

@@ -5,7 +5,7 @@
 
 EfficientNetB4 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.
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of EfficientNet-B4 found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/efficientnet.py). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/efficientnet_b4).
 

qai_hub_models/models/efficientnet_v2_s/README.md

@@ -5,7 +5,7 @@
 
 EfficientNetV2-s 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.
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of EfficientNet-V2-s found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/efficientnet.py). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/efficientnet_v2_s).
 

qai_hub_models/models/efficientvit_b2_cls/README.md

@@ -5,7 +5,7 @@
 
 EfficientViT 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.
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of EfficientViT-b2-cls found [here](https://github.com/CVHub520/efficientvit). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/efficientvit_b2_cls).
 

qai_hub_models/models/efficientvit_l2_cls/README.md

@@ -5,7 +5,7 @@
 
 EfficientViT 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.
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of EfficientViT-l2-cls found [here](https://github.com/CVHub520/efficientvit). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/efficientvit_l2_cls).
 

qai_hub_models/models/efficientvit_l2_seg/README.md

@@ -5,7 +5,7 @@
 
 EfficientViT is a machine learning model that can segment images from the Cityscape dataset. It has lightweight and hardware-efficient operations and thus delivers significant speedup on diverse hardware platforms
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of EfficientViT-l2-seg found [here](https://github.com/CVHub520/efficientvit). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/efficientvit_l2_seg).
 

qai_hub_models/models/esrgan/README.md

@@ -5,7 +5,7 @@
 
 ESRGAN is a machine learning model that upscales an image with minimal loss in quality.
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of ESRGAN found [here](https://github.com/xinntao/ESRGAN/). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/esrgan).
 

qai_hub_models/models/face_attrib_net/README.md

@@ -5,7 +5,7 @@
 
 Facial feature extraction and additional attributes including liveness, eyeclose, mask and glasses detection for face recognition.
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of FaceAttribNet found [here](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/face_attrib_net/model.py). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/face_attrib_net).
 

qai_hub_models/models/face_det_lite/README.md

@@ -5,7 +5,7 @@
 
 face_det_lite is a machine learning model that detect face in the images
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of Lightweight-Face-Detection found [here](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/face_det_lite/model.py). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/face_det_lite).
 

qai_hub_models/models/facemap_3dmm/README.md

@@ -5,7 +5,7 @@
 
 Real-time 3D facial landmark detection optimized for mobile and edge.
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of Facial-Landmark-Detection found [here](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/facemap_3dmm/model.py). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/facemap_3dmm).
 

qai_hub_models/models/facemap_3dmm_quantized/README.md

@@ -5,7 +5,7 @@
 
 Real-time 3D facial landmark detection optimized for mobile and edge.
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of Facial-Landmark-Detection-Quantized found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/facemap_3dmm_quantized).
 

qai_hub_models/models/fastsam_s/README.md

@@ -5,7 +5,7 @@
 
 The Fast Segment Anything Model (FastSAM) is a novel, real-time CNN-based solution for the Segment Anything task. This task is designed to segment any object within an image based on various possible user interaction prompts. The model performs competitively despite significantly reduced computation, making it a practical choice for a variety of vision tasks.
 
-{source_repo_details}This repository contains scripts for optimized on-device
+This is based on the implementation of FastSam-S found [here](https://github.com/CASIA-IVA-Lab/FastSAM). This repository contains scripts for optimized on-device
 export suitable to run on Qualcomm® devices. More details on model performance
 accross various devices, can be found [here](https://aihub.qualcomm.com/models/fastsam_s).