Token Factory Workshop
🔗 bit.ly/4cCCNzV
Pointers
- Workshop run file (this one):
bit.ly/4cCCNzV - slides (coming)
- community and support @ Nebius Discord
- join link
- Nebius.Build.SF hackathon channel - questions, finding teams ...etc
- Token Factory support
- Also see below for more resources
Prerequisites
Before starting the workshop, make sure you have:
- A Nebius Token Factory account
- (optinal) 🎁 credits. Use this link - activation code will be provided at the event
Workshop Theme
Building Production-Grade AI Applications
Modern AI applications improve continuously through a production feedback loop:
- Start with base (stock) models
- Collect production logs from real usage
- Fine-tune or shape models using real production data
- Deploy the improved model
This iterative process enables teams to progressively build robust, production-ready AI systems.
⭐️ Token Factory has the complete workflow built-in ⭐️
0 — Getting Started
Begin by setting up your environment and verifying access.
1 - Using Models
In this section, we explore how to use models hosted on Token Factory.
➡️ structured-output: Produce structured output like JSON from LLMs.
➡️ tool calling: Extend LLMs capability by providing them with functions/tools.
2 - Collecting Production Logs
Next, we capture real-world usage data to improve model performance.
3 - Customizing / Shaping Models
Learn how to adapt models for our specific use cases.
➡️ fine tuning models - improve model performance by training on production data and other optimizations.
➡️ Distilling models - create smaller, efficient models.
4 - Deploy and Monitor
Deploy trained models and monitor their performance in real time.
5 - Integration with Coding Agents
Integrate models with coding assistants like Cline, Cursor and Claude Code.
6 - Fun and Games
A few experimental and creative examples to explore what else is possible.
🐍 *snake game 🐍 - the classic snake game, but LLMs control the snakes in real time!
🪿 Pelican riding a bicycle - a fun 'vibe benchmark' to gauge model intelligence!
Resources
- Token Factory cookbook - lots of examples
- dev.nebius.com: Hub or nebius developer resources
- awesome ai apps - a great repo with lots of examples with Nebius Token Factory
Dev Notes
Project setup using uv:
uv init --python=3.12
uv add openai python-dotenv pydantic tavily-python
uv add --dev ipykernel
# (optional) generate requirements.txt
uv export \
--frozen \
--no-hashes \
--no-emit-project \
--no-default-groups \
--output-file=requirements.txt