Pinned Repositories
sm-model-serving-patterns
SageMaker Model Serving Patterns
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.
slm-innovator-lab
This lab is a 1-day/2-day end-to-end SLM workshop led and developed by AI GBB. Attendees will learn how to quickly and easily perform the data preparation-fine tuning-serving-LLMOps series of processes using Azure ML Studio and AI Studio, and will be able to expand the workload based on this.
synthetic-qa-generation
This hands-on lab aims to alleviate some of that headache by demonstrating how to create/augment a QnA dataset from complex unstructured data, assuming a real-world scenario. The sample aims to be step-by-step for developers and data scientists, as well as those in the field, to try it out with a little help.
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.
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.
sagemaker-studio-workshop-kr
Korean localized SageMaker Studio workshop materials for hands-on labs.
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.
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.
daekeun-ml's Repositories
daekeun-ml/evaluate-llm-on-korean-dataset
Performs benchmarking on two Korean datasets with minimal time and effort.
daekeun-ml/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.
daekeun-ml/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.
daekeun-ml/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.
daekeun-ml/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.
daekeun-ml/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.
daekeun-ml/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.
daekeun-ml/deepseek-r1-azureml
This is a simple example of how to serve a DeepSeek model with Azure ML.
daekeun-ml/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
daekeun-ml/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.
daekeun-ml/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.
daekeun-ml/end-to-end-pytorch-on-sagemaker
Building an end-to-end ML demo based on the PyTorch framework on SageMaker
daekeun-ml/sm-distributed-train-bloom-peft-lora
This hands-on labs modifies the Hugging Face PEFT fine-tuning and model deployment example on Amazon SageMaker.
daekeun-ml/triton-multi-model-endpoint
This hands-on provides a guide to SageMaker MME(Multi-Model-Endpoint) on GPU.
daekeun-ml/my-rag-project
daekeun-ml/sagemaker-distributed-training
Korean localization of the SageMaker Distributed Training notebooks added in AWS re:Invent 2020
daekeun-ml/AWS-LLM-SageMaker
SageMaker Ployglot based RAG opensearch
daekeun-ml/multinode-training-azureml
Distributed Training on Azure Starter Hands-on labs
daekeun-ml/synthetic-qa-generation
This hands-on lab aims to alleviate some of that headache by demonstrating how to create/augment a QnA dataset from complex unstructured data, assuming a real-world scenario. The sample aims to be step-by-step for developers and data scientists, as well as those in the field, to try it out with a little help.
daekeun-ml/AI-Gateway
APIM ❤️ OpenAI - this repo contains a set of experiments on using GenAI capabilities of Azure API Management with Azure OpenAI and other services
daekeun-ml/autogluon-imgclass-with-sagemaker-example
This is an example of low-code AutoML using AutoGluon to perform image classification quickly and easily.
daekeun-ml/autogluon-objdetect-with-sagemaker-example
This is an example of low-code AutoML using AutoGluon to perform object detection quickly and easily.
daekeun-ml/aws-chalice-examples
Guide to basic usage of AWS Chalice
daekeun-ml/aws-summit-aiml-demo
daekeun-ml/azure-genai-utils
This repository contains a set of utilities for working with Azure GenAI. The utilities are written in Python and are designed to be used for Hackathons, Workshops, and other events where you need to quickly get started with Azure GenAI.
daekeun-ml/Azure_OpenAI_samples
daekeun-ml/fastertransformer_backend
daekeun-ml/ft-triton
daekeun-ml/generative-ai-sagemaker-cdk-demo
Deploy Generative AI models from Amazon SageMaker JumpStart using AWS CDK
daekeun-ml/ko-trocr-dataset-poc