SECAI LLM Training

This is a collection of Jupyter Notebooks about basic and advanced LLM usage, focusing on what’s possible with the ScaDS.AI Large Language Models (LLM) Services (VPN required). It aims at Python programmers in SECAI who want to dive into LLMs for generating text, code and data using open source/weights models.

Contributions and feedback are very welcome! In case you see room for improvement, please create a github issue and/or consider contributing.

Topics

The notebook collection aims covering these topics:

• Large Language Models (LLMs)

• Text/Code/Data generation

• Prompt Engineering

• Retrieval-augmented-generation

• Function calling

• Agents

Covered Python libraries and software

In these notebooks we use non-standard libraries from the GenAI field. Installation instructions can be found either in the first chapter or in the readme of the respective subchapter.

• bia-bob

• llama-index

• ollama

• openai

Covered models

We will explore how these models work

• meta-llama/Llama-3.3-70B-Instruct

• DeepSeek-Coder-V2-Lite

Videos

The materials provided here were also discussed in a couple of recorded Online Lectures

• Large Language Models for Bio-image Analysis (ScaDS.AI Living Lab lecture 2024)

• Large Language Models – an introduction for life scientists (GloBIAS Seminar 2024)

• Bio-image Analysis Code Generation (I2K Conference 2024)

• Generative Artificial Intelligence for Bio-image Analysis

Slide decks

Also training slides will be open access [soon].

Related resources

The notebooks presented here were partially taken from other places or inspired by code in these resources:

• https://scads.github.io/generative-ai-notebooks/intro.html

• https://platform.openai.com/docs/guides/images/usage

• ScaDS/prompting-with-api

• haesleinhuepf/simple-rag

• haesleinhuepf/simple-chat-with-docs

• ScaDS/BIDS-lecture-2024

• https://scads.github.io/prompt-engineering-tutorial-2023/

• haesleinhuepf/prompting-pptx

• haesleinhuepf/bia-bob

Acknowledgements

We acknowledge the financial support by the Federal Ministry of Education and Research of Germany and by Sächsische Staatsministerium für Wissenschaft, Kultur und Tourismus in the programme Center of Excellence for AI-research „Center for Scalable Data Analytics and Artificial Intelligence Dresden/Leipzig“, project identification number: ScaDS.AI