AWS LLM SageMaker

AWS-LLM-SageMaker

This hands-on workshop for developers and solution builders introduces how to leverage Foundation Models (FM) with Amazon SageMaker.

In this lab, we'll show you some of our customers' most popular use patterns for Generative AI and examples of technologies that use GenAI to drive value for their organizations by improving productivity.
This can be achieved by leveraging foundational models that help you compose emails, summarize text, answer questions, build chatbots, and create images.

Guide to AWS Samples Github deployment practice materials

This lab material is distributed on AWS Samples Github. Current practice materials are always more up-to-date than the official AWS Samples materials.

LLM - RAG: Opensearch with SageMaker Endpoint LLM Polyglot

• Topic: LLM - RAG: Opensearch with SageMaker Endpoint LLM Polyglot
• Reflection link: https://github.com/aws-samples/aws-ai-ml-workshop-kr/tree/master/genai/aws-gen-ai-kr/20_applications/04_rag_finance_opensearch_sllm_workshop
• Latest reflection date: 2024.04.25

[Tuner] QLoRA fine-tuning

• Topic: [Tuner] QLoRA fine-tuning
• Reflection link: https://github.com/aws-samples/aws-ai-ml-workshop-kr/tree/master/genai/aws-gen-ai-kr/30_fine_tune/01-instruction-tuning-peft-qlora
• Latest reflection date: 2024.04.18

LLM - RAG: Opensearch with SageMaker Endpoint LLM Ployglot

1. Hands-on implementation of RAG (Retrieval-Augmented Generation) with Amazon SageMaker and Amazon Opensearch - RAG (Retrieval-Augmented Generation) is an innovative NLP architecture that combines information retrieval and text generation. In this hands-on lab, you will learn through a brief hands-on exercise how RAG integrates with Amazon Opensearch to enhance the process of searching external trusted databases or documents. In this lab, you'll gain hands-on experience implementing these patterns in SageMaker Endpoint and Amazon Openssearch through embedding data input, SDKs, and open source software such as LangChain and FAISS.

[Tuner] QLoRA fine-tuning

• KULLM-Polyglot-12.8B

Filenames

• 1_prepare-dataset-alpaca-method.ipynb : Prepare a training dataset from the instruction dataset. This method tokenizes each sample.
• 1_prepare-dataset-chunk-method.ipynb : Prepare a training dataset from the instruction dataset. This method concatenates all samples and divides them according to the chunk size.
• 2_local-train-debug-lora.ipynb : Debug with some sample data in the development environment before performing in earnest on the training instance. If you are already familiar with fine tuning, please skip this hands-on and proceed with 3_sm-train-lora.ipynb.
• 3_sm-train-lora.ipynb : Performs fine tuning on SageMaker training instances.