Workshop invite: Install your own private chatGPT (with private data) with Helix.ml! 😃
Private local GenAI with knowledge and API integrations - first workshop 1pm PT today
We are running our first local GenAI workshop today at 1pm PT! (Other dates also available)
Come join us 😻 https://bit.ly/helix-workshops
Sign up if you'd like to participate in this free 2-part workshop online!
Requirements:
Linux, macOS, or Windows
Ability to install Docker
4 CPUs, 8GB RAM and 50GB+ free disk space
A fast internet connection
NVIDIA GPU not required for part 1 of the workshop
Let us know if you don’t have any of the above! → DX@helix.ml
Getting help:
Discord: https://discord.gg/VJftd844GE
Slack (MLOps Community): https://gatewaze.mlops.community/#email --> #helix
Plan ahead! You'll have a better experience by completing these steps ahead of time:
Install Docker Desktop: https://docs.docker.com/desktop/get-started/ (homebrew option: https://formulae.brew.sh/formula/docker) Note: make sure that you’re logged in to your docker account
Install Ollama Server
https://ollama.com/
(homebrew options: https://formulae.brew.sh/formula/ollama
3. Download Ollama Model
> ollama pull llama3:instruct
Workshop Part 1 (1 hour):
Intro to GenAI terminology and concepts
Install a private “chatGPT” from on your laptop via Helix.ml! (source available)
Practice loading private sample data/sample APIs
Some inference and fine-tuning practice
Workshop Part 2 (1 hour)
Install a private "chatGPT" using your own GPUs
Try more models and capabilities with GPUs
Deep dive with your own data (private sessions available).
Deep dive with your API needs.
Learn best practices for image models, fine-tuning, etc
Learn about future workshops for challenges such as running LLMs on Kubernetes
Part 2 workshop requirements:
a VM (eg. on Digital Ocean, Google, etc.)
GPUs (eg. runpod.io)
a domain name with access to DNS settings
Any questions? email DX@helix.ml