Small is beautiful — using and adapting small language models

Due to high demand, we are offering this workshop a second time. Please note that the content will be the same as in the workshop on 27/05. If you have already attended this session, there is no need to join again.

This is a hands-on workshop to use and adapt small language models (SLM) running locally on your laptop. Check out https://huggingface.co/blog/jjokah/small-language-model for an overview on what is a SLM.
The goals of this workshop are not only technical but much more importantly:

• to raise awareness on alternatives to the usual online AI solutions
• to give agency and choices back to users of AI, for fitting use cases at least, and
• to discuss how such alternatives align with the Code of Conduct Democratic AI

Local-first SLM may also be a better fit when it comes to volunteer projects for nonprofits, where we often cannot afford paying online subscriptions.
Too good to be true? Join this beginner-friendly workshop to try SLM out for yourself! If you have NEVER heard of SLM, Llama.cpp, Ollama, LM Studio, llamafile or RAG before, this workshop is for you. On the other hand if you already have some experience on SLM and would like to dive deeper with us, kindly stay tuned for the follow-up, more advanced workshop.

Our rundown:

• Motivation and goals
• What are small language models (SLM)
• Finding a SLM for your laptop
• Setting parameters for a SLM
• Adapting an existing SLM with private or the latest info
• Using SLM from the Python programming language
• Open exchange on pros, cons and follow-up ideas

Sylvi and Chris will be leading this workshop. Sylvi is an economist gone data scientist, currently serves on the Board of CorrelAid and is interested in establishing the code of conduct of democratic AI (https://demokratische-ki.de/) into CorrelAid’s structure. Chris is one of CorrelAid's Local Chapter Heads in Cologne, a career IT person with over 30 years experience working worldwide.

Please install LM Studio at https://lmstudio.ai/ before the workshop, and note the followings:

• This event will be conducted in English.
• This event follows the CorrelAid Code of Conduct.
• There will be NO recording of the session.
• AI bots for transcription are not allowed.
• Participants are limited to 12