Free GPU Workshop: Fine-Tune Your Own Text-to-SQL Model on an Nvidia H100 GPU
Details
Fine-tune an open-source model to write SQL, on your own free GPU lab. Bring a laptop and a browser; we bring the GPU.
Every attendee gets a private JupyterLab on an NVIDIA H100 GPU slice (about 10 GB of GPU memory), ready when you log in.
You will:
▪ Score a small open model (Qwen2.5-Coder 1.5B) on 50 SQL questions
▪ Fine-tune it with LoRA on real question-to-SQL examples
▪ Rerun the same questions and compare before and after
▪ Download your trained model and the notebooks
Who it’s for: anyone with basic Python and SQL. No ML background needed.
When: Wednesday, December 16, 2026, 5:00 PM ET, 1 hour, online.
Seats: limited to the GPU labs available.
RSVP: https://luma.com/p3k7vylm
Labs set up with labagent, our open-source lab tool:
github.com/becloudready/labagent
