Deploying Large Language Models Locally

Content

Large Language Models (LLMs) are a class of machine learning models that have recently gained a lot of attention.  These models  are trained on large amounts of data and after training can be used  in many applications. 
Although models from OpenAI and Google can be used as services online, it is often desirable to have a model that can be used offline. This training will show you how to deploy and use such models locally.

Learning Objectives

• understand what LLMs are and how they are trained;
• be able to use a pre-trained LLM for text generation;
• be able to use Retrieval Augmented Generation (RAG) for question answering on your own data;
• understand how quantization works and how it can be used to reduce the size of a model;
• be able to fine-tune a pre-trained LLM for a specific task. 

Target audience 

This training is for you if you need to deploy Large Language  Models (LLMs) on your own infrastructure. 

Prior knowledge

• You will need experience programming in Python.  This is not a training that starts from scratch.
• Familiarity with Linux or HPC environments is recommended.