Skip to content

fw-ai/cookbook

Repository files navigation

Fireworks AI Cookbook

Ready-to-run training recipes for reinforcement learning (GRPO, DAPO, GSPO, CISPO), preference optimization (DPO, ORPO), and supervised fine-tuning (SFT) on Fireworks.

Full documentation: Fireworks Training SDK Reference

Quick Start

git clone https://github.com/fw-ai/cookbook.git
cd cookbook/training
conda create -n cookbook python=3.12 -y && conda activate cookbook
pip install --pre -e .

See training/README.md for configuration, recipes, and examples.

For AI Agents

The primary reference for agents working in this repo is skills/dev/SKILL.md — it maps tasks and error signals to specific reference files. Start there, not the READMEs.

Repository Structure

Only training/ is actively developed. Other top-level directories (integrations/, multimedia/, archived/) are kept for backward compatibility.

training/           Training SDK recipes, utilities, and examples
  recipes/          Fork-and-customize training loop scripts
  utils/            Shared config, data loading, losses, metrics
  examples/         Worked examples (RL, SFT, DPO, ORPO)
  verifier/         Renderer correctness validator + live React viewer
  tests/            Unit and end-to-end tests
skills/             Agent skills and reference docs

Fireworks Agent skill

  • skills/fireworks-agent/SKILL.md — end-to-end fine-tuning via the Fireworks Agent (firectl session). Give it one natural-language instruction and it handles data inspection, model selection, hyperparameter sweeps, training, evaluation, and deployment. Includes the full session lifecycle: create, stream events, answer the agent's mid-run questions, recover from failures, and clean up.

Contributing

See the Contribution Guide.

Support