Update README.md

Author: eitansela

README.md

@@ -55,14 +55,14 @@ The repository contains the following resources:
  - [**TensorFlow Script Mode Debug Training Script**](tensorflow_script_mode_debug_local_training): This example shows how to debug your training script running inside a prebuilt SageMaker Docker image for TensorFlow, on your local machine using SageMaker local mode.
  - [**TensorFlow Script Mode Deploy a Trained Model and inference on file from S3**](tensorflow_script_mode_local_model_inference): This example shows how to deploy a trained model to a SageMaker endpoint, on your local machine using SageMaker local mode, and inference with a file in S3 instead of http payload for the SageMaker Endpoint.
  - [**TensorFlow Script Mode Training and Batch Transform**](tensorflow_script_mode_california_housing_local_training_and_batch_transform): This example shows how to train your model and run Batch Transform job with TensorFlow and SageMaker script mode, on your local machine using SageMaker local mode.
- - [**Extending SageMaker TensorFlow Deep Learning Container Image**](tensorflow_extend_dlc_california_housing_local_training): In this example we show how to package a TensorFlow container, extending the SageMaker TensorFlow training container, with a Python example which works with the California Housing dataset. By extending the SageMaker TensorFlow container we can utilize the existing training solution made to work on SageMaker, leveraging SageMaker TensorFlow `Estimator` object, with `entry_point` parameter, specifying your local Python source file which should be executed as the entry point to training. To make it work, we replace the `framework_version` and `py_version` parameters, with `image_uri` of the Docker Image we have created. This sample code can run on your local machine using SageMaker local mode. 
+ - [**Extending SageMaker TensorFlow Deep Learning Container Image**](tensorflow_extend_dlc_california_housing_local_training): In this example we show how to package a TensorFlow container, extending the SageMaker TensorFlow training container, with a Python example which works with the California Housing dataset. By extending the SageMaker TensorFlow container we can utilize the existing training solution made to work on SageMaker, leveraging SageMaker TensorFlow `Estimator` object, with `entry_point` parameter, specifying your local Python source file which should be executed as the entry point to training. To make it work, we replace the `framework_version` and `py_version` parameters, with `image_uri` of the Docker Image we have created. This sample code can run on your local machine using SageMaker local mode.
 
 - **PyTorch resources:** 
 
  - [**PyTorch Script Mode Training and Serving**](pytorch_script_mode_local_training_and_serving): This example shows how to train and serve your model with PyTorch and SageMaker script mode, on your local machine using SageMaker local mode.
  - [**PyTorch Script Mode Deploy a Trained Model**](pytorch_script_mode_local_model_inference): This example shows how to deploy a trained model to a SageMaker endpoint, on your local machine using SageMaker local mode, and serve your model with the SageMaker Endpoint.
- - [**Deploy a pre-trained PyTorch HeBERT model from Hugging Face on Amazon SageMaker Endpoint**](huggingface_hebert_sentiment_analysis_local_serving): This example shows how to deploy a pre-trained PyTorch HeBERT model from Hugging Face, on Amazon SageMaker Endpoint, on your local machine using SageMaker local mode.
- - [**Deploy a pre-trained PyTorch YOLOv5 model on Amazon SageMaker Endpoint**](pytorch_yolov5_local_model_inference): This example shows how to deploy a pre-trained PyTorch YOLOv5 model on Amazon SageMaker Endpoint, on your local machine using SageMaker local mode.
+ - [**Deploy a pre-trained PyTorch HeBERT model from Hugging Face on SageMaker Endpoint**](huggingface_hebert_sentiment_analysis_local_serving): This example shows how to deploy a pre-trained PyTorch HeBERT model from Hugging Face, on SageMaker Endpoint, on your local machine using SageMaker local mode.
+ - [**Deploy a pre-trained PyTorch YOLOv5 model on SageMaker Endpoint**](pytorch_yolov5_local_model_inference): This example shows how to deploy a pre-trained PyTorch YOLOv5 model on SageMaker Endpoint, on your local machine using SageMaker local mode.
 
 - **Bring Your Own Container Training resources:** 
 
@@ -86,8 +86,10 @@ The repository contains the following resources:
  - [**Delta Sharing Bring Your Own Container Processing Job**](delta_sharing_bring_your_own_container_local_processing): This example provides a detailed walk-through on how to package a scikit-learn Docker image for processing job that fetch data from a table on Delta Lake using Delta Sharing, and aggregate total COVID-19 cases per country. We have included also a Python file for processing jobs that can run on your local computer, for faster development.
  - [**Dask Bring Your Own Container Processing Job**](dask_bring_your_own_container_local_processing): This example provides a detailed walk-through on how to package a Dask Docker image for processing job that fetch JSON file from a website, and outputs the filenames found. We have included also a Python file for processing jobs that can run on your local computer, for faster development.
 
-- **Bring Your Own Container MacBook M1/ARM/Apple Silicon resources:** 
+- **Graviton resources - will work only on MacBook M1/ARM/Apple Silicon:** 
 
+- [**Deploy a pre-trained TensorFlow model on SageMaker Graviton Endpoint**](tensorflow_graviton_script_mode_local_model_inference): This example shows how to deploy a pre-trained TensorFlow model on SageMaker Graviton Endpoint, using your local machine using SageMaker local mode.
+- [**Deploy a pre-trained PyTorch CIFAR-10 model on SageMaker Graviton Endpoint**](pytorch_graviton_script_mode_local_model_inference): This example shows how to deploy a pre-trained PyTorch CIFAR-10 model on SageMaker Graviton Endpoint, using your local machine using SageMaker local mode.
 - [**Bring Your Own Container scikit-learn Algorithm - Train/Serve**](scikit_learn_graviton_bring_your_own_container_local_training_and_serving): This example provides a detailed walkthrough on how to package a scikit-learn algorithm for training and production-ready hosting. We have included also a Python file for local training and serving that can run on your local M1 MacBook computer, for faster development.
 - [**Bring Your Own Container TensorFlow Algorithm - Train**](tensorflow_graviton_bring_your_own_california_housing_local_training): This example provides a detailed walkthrough on how to package a TensorFlow algorithm for training. We have included also a Python file for local training that can run on your local M1 MacBook computer, for faster development.
 - [**Bring Your Own Container TensorFlow Algorithm - SageMaker Training Toolkit**](tensorflow_graviton_bring_your_own_california_housing_local_training_toolkit): This example provides a detailed walkthrough on how to package a TensorFlow algorithm for training using the SageMaker Training Toolkit. We have included also a Python file for local training that can run on your local M1 MacBook computer, for faster development.