In this workshop, we demonstrate how to use Amazon SageMaker and various strategies to fine tune LLMs. The goal of this workshop is to give you hands-on experience with fine-tune / deploying foundation models using Amazon SageMaker

What's included in the workshop

This workshop tackles the following topics -

• Lab 1: Fine-tune a Llama-based LLM.
• Lab 2: Multi-LoRA adapter inference on Amazon SageMaker.
• Lab 3: Deploy LLMs with SageMaker Jumpstart UI
• Lab 4: Setup a LLM Playground on SageMaker Studio
• Lab 5: Prompt Engineering with LLMs on SageMaker Studio.
• Lab 6: Contextual chatbot using Llama2 via SageMaker JumpStart and Amazon OpenSearch Serverless with Vector Engine

Security

See CONTRIBUTING for more information.

License

This library is licensed under the MIT-0 License. See the LICENSE file.