Skip to content

nhsengland/llm_tutorial

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

LLM Tutorial

This repo contains notebooks which walk you through some simple LLM implementations. It uses free software and can all be run inside Google Collab, for maximum accessibility.

You can open the tutorial here: Open In Colab

Contact

This repo is currently maintained by @samhollings and @adamhollings - raise and issue or a pull request if you have any suggestions (or just contact us directly!)

Description

This repo contains a tutorial showcasing how simple it is to begin using open-source LLMs in Python.

It shows the use of three models:

  • Phi3
  • Grammarly CoEdit
  • Cappy

The tutorial is designed to be run in Google Colab - to allow it to be freely and easily used by anyone who wants to learn.

Prerequisites

  • knowledge-wise, some ability with python. Knowledge of data science would be useful, but not crucial (at least at the start). Interest in LLMs will help!
  • system-wise: the requirements can be found in the requirements.txt file, and can be loaded pip.

Getting Started

Google Colab

Open one of the Google Colab links above! This repo is meant to be used in Google Colab for demo and teaching purposes.

Clone the repo

Clone the repository. To learn about what this means, and how to use Git, see the Git guide.

git clone <insert URL>

install dependencies

Make a virtual environment and install the dependencies:

pip install -r requirements.txt

Adapting for your project

Just take whatever code you need, and reimplement it. This was made mostly in the form of Jupyter notebooks for ease of use and demos, however I wouldn't recommend that for most applications - but it can be very useful when getting started and playing with the code.

Licence

The LICENCE file will need to be updated with the correct year and owner

Unless stated otherwise, the codebase is released under the MIT License. This covers both the codebase and any sample code in the documentation.

About

A tutorial about learning to build an LLM using open source tools.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published