daekeun-ml/aiot-e2e-sagemaker-greengrass-v2-nvidia-jetson

Stars
2
Language
Jupyter Notebook
License
MIT No Attribution
Created over 3 years ago
Updated about 3 years ago

daekeun-ml/aiot-e2e-sagemaker-greengrass-v2-nvidia-jetson

daekeun-ml

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Hands-on lab from ML model training to model compilation to edge device model deployment on the AWS Cloud. It covers the detailed method of compiling SageMaker Neo for the target device, including cloud instance and edge device, and how to write and deploy Greengrass-v2 components from scratch.

evaluate-llm-on-korean-dataset

Performs benchmarking on two Korean datasets with minimal time and effort.

genai-ko-LLM

This hands-on lab walks you through a step-by-step approach to efficiently serving and fine-tuning large-scale Korean models on AWS infrastructure.

Jupyter Notebook

KoSimCSE-SageMaker

This is a hands-on for ML beginners to perform SimCSE step-by-step. Implemented both supervised SimCSE and unsupervisied SimCSE, and distributed training is possible with Amazon SageMaker.

Jupyter Notebook

sm-huggingface-kornlp

This hands-on lab guides you on how to easily train and deploy Korean NLP models in a cloud-native environment using SageMaker's Hugging Face container.

Jupyter Notebook

sagemaker-studio-workshop-kr

Korean localized SageMaker Studio workshop materials for hands-on labs.

Jupyter Notebook

sm-kornlp-usecases

SageMaker-based fine-tuning and deployment hands-on example of a Korean NLP downstream task. Recommended for customers considering adopting NLP workloads on AWS.

Jupyter Notebook

tensorflow-in-sagemaker-workshop

Localized (Korean) Tensorflow in SageMaker workshop materials for hands-on labs

Jupyter Notebook

sm-distributed-training-step-by-step

This repository provides hands-on labs on PyTorch-based Distributed Training and SageMaker Distributed Training. It is written to make it easy for beginners to get started, and guides you through step-by-step modifications to the code based on the most basic BERT use cases.

Jupyter Notebook

azure-llm-fine-tuning

This hands-on walks you through fine-tuning an open source LLM on Azure and serving the fine-tuned model on Azure. It is intended for Data Scientists and ML engineers who have experience with fine-tuning but are unfamiliar with Azure ML.

Jupyter Notebook

tfs-workshop

Deep Learning Inference hands-on labs; Learn how to host pre-trained TensorFlow/MXNet models to Amazon SageMaker Endpoint without building Docker Image

Jupyter Notebook

time-series-on-aws-hol

Time-series data hands-on lab on AWS for Data Scientists and Developers. Preprocessing, training and deployment using GluonTS and Amazon SageMaker.

Jupyter Notebook

aws-inferentia

This repository provides an easy hands-on way to get started with AWS Inferentia. A demonstration of this hands-on can be seen in the AWS Innovate 2023 - AIML Edition session.

Jupyter Notebook

blazingtext-workshop-korean

AWS SageMaker Workshop materials for hands-on labs; Word Embedding and Text Classification Using BlazingText

Jupyter Notebook

sagemaker-reinvent2019-kr

Korean localization of the SageMaker notebooks added in AWS re:Invent 2019

Jupyter Notebook

recommendation-workshop

Recommendation system Hand-on Lab. Translated and modified original personalize hands-on lab to make it more appropriate for the workshop, and added Factorization Machine-based recommendation example.

Jupyter Notebook

ggv2-cv-mlops-workshop

AWS IoT Greengrass V2 Hands-on Lab for Image classification and Object Detection. It guides both how to develop artifacts from the scratch and how to to deploy your own model from public components.

end-to-end-pytorch-on-sagemaker

Building an end-to-end ML demo based on the PyTorch framework on SageMaker

Jupyter Notebook

autogluon-on-aws

This hands-on lab covers example codes for Tabular, NLP, CV, SageMaker, HPO, and is suitable for self-study and half-day or full-day workshops.

Jupyter Notebook

kobert-workshop

Hands-on Lab to perform KoBERT fine-tuning and inference on Amazon SageMaker. Also supports Multi-GPU training.

Jupyter Notebook

sagemaker-studio-end-to-end

This hands-on lab is a Korean translated version of the official example code of Architect and build the full machine learning lifecycle with AWS. You can practice the SageMaker End-to-end pipeline in about 1 hour 30 minutes to 2 hours.

Jupyter Notebook

triton-multi-model-endpoint

This hands-on provides a guide to SageMaker MME(Multi-Model-Endpoint) on GPU.

Jupyter Notebook

sm-distributed-train-bloom-peft-lora

This hands-on labs modifies the Hugging Face PEFT fine-tuning and model deployment example on Amazon SageMaker.

Jupyter Notebook

my-rag-project

sagemaker-distributed-training

Korean localization of the SageMaker Distributed Training notebooks added in AWS re:Invent 2020

Jupyter Notebook

sm-inference-new-features

SageMaker new features (multi-container endpoint, async inference, serverless inference) hands-on. It can be used more practically than the official examples, and inference examples for Korean NLP models have been added.

Jupyter Notebook

architecting-for-ml-on-aws

Jupyter Notebook

sagemaker-yolo-finetune-workshop

Jupyter Notebook

gitbook

sagemaker-rl-kr

Korean localized SageMaker RL(Reinforcement Learning) jupyter notebook examples.

Jupyter Notebook

sagemaker-pipelines

Korean localization of the SageMaker Pipelines notebooks added in AWS re:Invent 2020

Jupyter Notebook

sagemaker-byos-byoc

Amazon SageMaker BYOS & BYOC hands-on labs. Designed for a 4-hour SageMaker workshop.

Jupyter Notebook

homecredit-byoc-lightgbm

Hands-on that performs training and inference on SageMaker by pushing LightGBM to ECR as BYOC(Bring Your Own Container).

Jupyter Notebook