# Open source models Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/open-source-models
> Markdown URL: https://aitinkerers.org/technologies/open-source-models.md
> Technology record last updated: 2026-02-26T12:16:41Z
> Generated: 2026-09-22T18:40:23Z

Open-source models (OSMs) democratize AI: they provide transparent, customizable foundation model weights (e.g., Llama 3, Mixtral) for flexible, local deployment.

Open-source models are AI technologies where the source code and pre-trained weights are freely available (Apache 2.0 or custom licenses). This transparency gives developers full control: they can inspect, modify, and fine-tune the model for specific, high-accuracy use cases, like fraud detection or specialized medical analysis. Key players like Meta (Llama 3.1, up to 405B parameters) and Mistral AI (Mixtral 8x22B MoE) drive this ecosystem, often hosted on central platforms like Hugging Face. Deploying these models locally or on custom hardware reduces vendor lock-in, enhances data security, and accelerates community-driven innovation.

- Official technology site: https://huggingface.co/models
- Public AI Tinkerers demos and talks: 7
- Result page: 1 of 1

## Recent Public Talks and Demos

### [AI safety in healthcare](https://vienna.aitinkerers.org/talks/rsvp_jm2eqpK8Vtk)

AI by itself is currently not good enough to be used without extensive supervision in the professional/production environment of a lot of industry, especially law enforcement or healthcare. Because of that, I would talk about how I design a more safe and deterministic AI system for industries that require a high level of complexity, accuracy, and certainty. I would walk through one of the project related to my award-wining research at AI in health conference of Ken Kennedy Institute of Rice University where I evaluate AI system for safety, before implementing solutions to mitigate those limitations. This include closely evaluating accuracy and saftey of AI outputs with feedback loop and "AI-as-a-judge", LLM jailbreaking, and careful prompt engineering

- Event context: AI Tinkerers Vienna: 2026 — 2026-02-19 — Vienna
- Public talk page: https://vienna.aitinkerers.org/talks/rsvp_jm2eqpK8Vtk

### [Building a Multimodal Multi-Agent Chatbot with Feedback Mechanism and Reinforcement Learning Loop](https://atlanta.aitinkerers.org/talks/rsvp_b782UfRe8WQ)

This presentation demonstrates the development of a multimodal, multi-agent chatbot using open-source models to handle text, image, and audio inputs without proprietary APIs. It integrates tools like LangGraph and ReactJsonAgent for agent orchestration and leverages feedback mechanisms for continuous improvement. As a relevant part 2 - A brief overview (and sample project) to show the power of reinforcement learning techniques like RLHF with PPO (and some custom results of improvement on another project's data) to utilize human feedback to further fine-tune models

- Event context: AI Tinkerers Atlanta November Meetup — 2024-11-19 — Atlanta
- Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_b782UfRe8WQ

### [AI agents for investment research](https://la.aitinkerers.org/talks/rsvp_WaoS2XyFySY)

Using various ai personas to do the aspects of financial analysis based on their personas (fundamental analysis, technical analysis, growth and innovation analysis etc)

- Event context: May 21st - LA AI Tinkerers Meetup & Demos — 2024-05-22 — Los Angeles
- Public talk page: https://la.aitinkerers.org/talks/rsvp_WaoS2XyFySY

### [Self-Rewarding Language Models](https://la.aitinkerers.org/talks/rsvp_Lll5VHsQKbQ)

We reproduced the Self-Rewarding Language Model paper from the team at MetaAI but with open source models

- Event context: March 19th - LA AI Tinkerers Meetup & Demos — 2024-03-20 — Los Angeles
- Public talk page: https://la.aitinkerers.org/talks/rsvp_Lll5VHsQKbQ

### [AI Coding with repository context](https://london.aitinkerers.org/talks/rsvp_mJJgD012OXc)

The world of AI assisted coding is moving at a blazing fast speed. There are numerous products and models which excel at various different aspects of the coding experience. We will go from copilot based code generation, to using AI to convert your prompt to edits in the codebase and possible ideas to fine-tune on a codebase and make LLMs understand a new codebase. The rise of open source models has also made it possible for anyone to run their own local copilot, these models can be coached to fit your own usecase quite easily when prompted and fine-tuned for your usecase.

- Event context: AI Tinkerers London - January Meetup — 2024-01-30 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_mJJgD012OXc

### [Running quantized LLMs locally](https://boston.aitinkerers.org/talks/rsvp_NYD2oF8oenI)

Running smaller quantized open source models on your own computer is getting popular, I thought I would demo how I do that with llama.cpp

- Event context: January 2024 Tinkerers Unite! — 2024-01-22 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_NYD2oF8oenI

### [Stable Video + SDXL Turbo experiments](https://seattle.aitinkerers.org/talks/rsvp_w7engekiPyk)

Generate images faster than you can type with SDXL Turbo, and then transform those images to video with Stable Video. We made a free app to let anyone do this themselves. Early access to the app is live now at https://app.decohere.ai/turbo , and the password is "gottagofast"

- Event context: AI Tinkerers Seattle - December Meetup — 2023-12-13 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_w7engekiPyk

## Related Technologies

- [AI personas](https://aitinkerers.org/technologies/ai-personas) ([Markdown](https://aitinkerers.org/technologies/ai-personas.md)) — 1 public demo
- [Claude](https://aitinkerers.org/technologies/claude) ([Markdown](https://aitinkerers.org/technologies/claude.md)) — 174 public demos
- [Codebase](https://aitinkerers.org/technologies/codebase) ([Markdown](https://aitinkerers.org/technologies/codebase.md)) — 2 public demos
- [DeepSeek](https://aitinkerers.org/technologies/deepseek) ([Markdown](https://aitinkerers.org/technologies/deepseek.md)) — 12 public demos
- [Fine-tuning](https://aitinkerers.org/technologies/fine-tuning) ([Markdown](https://aitinkerers.org/technologies/fine-tuning.md)) — 20 public demos
- [Foundational Models](https://aitinkerers.org/technologies/foundational-models) ([Markdown](https://aitinkerers.org/technologies/foundational-models.md)) — 3 public demos
- [function calling](https://aitinkerers.org/technologies/function-calling) ([Markdown](https://aitinkerers.org/technologies/function-calling.md)) — 11 public demos
- [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 188 public demos
- [GitHub Copilot](https://aitinkerers.org/technologies/github-copilot) ([Markdown](https://aitinkerers.org/technologies/github-copilot.md)) — 20 public demos
- [LangGraph](https://aitinkerers.org/technologies/langgraph) ([Markdown](https://aitinkerers.org/technologies/langgraph.md)) — 67 public demos
- [llama](https://aitinkerers.org/technologies/llama) ([Markdown](https://aitinkerers.org/technologies/llama.md)) — 48 public demos
- [Local Inference](https://aitinkerers.org/technologies/local-inference) ([Markdown](https://aitinkerers.org/technologies/local-inference.md)) — 2 public demos
- [Local Models](https://aitinkerers.org/technologies/local-models) ([Markdown](https://aitinkerers.org/technologies/local-models.md)) — 1 public demo
- [Meta AI](https://aitinkerers.org/technologies/meta-ai) ([Markdown](https://aitinkerers.org/technologies/meta-ai.md)) — 1 public demo
- [OpenAI](https://aitinkerers.org/technologies/openai) ([Markdown](https://aitinkerers.org/technologies/openai.md)) — 112 public demos
- [PPO](https://aitinkerers.org/technologies/ppo) ([Markdown](https://aitinkerers.org/technologies/ppo.md)) — 2 public demos
- [Prompt Engineering](https://aitinkerers.org/technologies/prompt-engineering) ([Markdown](https://aitinkerers.org/technologies/prompt-engineering.md)) — 28 public demos
- [quantization](https://aitinkerers.org/technologies/quantization) ([Markdown](https://aitinkerers.org/technologies/quantization.md)) — 3 public demos