Skip to main content

Ctrl+K

Site Navigation

Setting up your computer
Prompting basics
Accessing LLMs
Chatbots
Function / Tool calling

Image generation

Image manipulation

Generating Videos, Books, Slides and online content

Code generation

Vision language models

Retrieval Augmented Generation

Model Fine-Tuning in the cloud

Model Fine-Tuning locally

Site Navigation

Setting up your computer
Prompting basics
Accessing LLMs
Chatbots
Function / Tool calling

Image generation

Image manipulation

Generating Videos, Books, Slides and online content

Code generation

Vision language models

Retrieval Augmented Generation

Model Fine-Tuning in the cloud

Model Fine-Tuning locally

Ctrl+K

Generative Artificial Intelligence Notebooks

Setup

Setting up your computer
- Installation instructions for Scientific Computing Uni Leipzig (paula)

LLM basics

Prompting basics
Accessing LLMs
Chatbots
- Programming an LLM-based chatbot
- A Chatbot GUI
Function / Tool calling
- Function calling using ollama
- Function calling using ScaDS.AI’s LLM service

Multi-Modal LLMs

Image generation
Image manipulation
Generating Videos, Books, Slides and online content
Code generation
Vision language models

Advanced Prompt Engineering

Retrieval Augmented Generation
Chat with Docs
Agents
Model Fine-Tuning in the cloud
Model Fine-Tuning locally
Benchmarking

Links

Imprint

repository
open issue

.md

Benchmarking

Benchmarking#

In this section we will benchmark LLMs solving task such as image describing and code generation.

previous

Uploading training data to the Huggingface Hub

next

Optimizing image generation prompting using CLIP scores

By Robert Haase

Last updated on 2025-01-15.

Copyright: Licensed CC-BY 4.0 unless mentioned otherwise. Contributions and feedback are welcome.