Train Your Own LLM - companion code
Chapter 13: Launch Day: Your Model Goes Live

HOW TO RUN
Use the Python environment from Chapter 4 (Python 3.12 or 3.13,
versions pinned in Appendix F). Unzip this folder, cd into it, and run each
script with: python <script>.py   (each example's caption in the book
gives its file name). Expected output is printed in the book.
Scripts download models and datasets from the Hugging Face Hub on first run.

CHAPTER NOTES
Serving tools: llama.cpp (tag b11513) or Ollama 0.40.x, plus pip install openai gradio
sentence-transformers. GGUF model files are not included (multi-GB); build them
with the Chapter 13 recipes. Windows, macOS, cloud, vLLM and SGLang recipes are
marked in the book as not run on our test machine.

FILES THAT NEED A GPU
- None. Every script here ran on a CPU-only test machine,
  except any recipe the book marks as not run on our test machine.

FILES
- ch13_guard_eval.py
- ch13_quant_score.py
- ch13_rag_eval.py
- shop_style_test.jsonl
- shop_messy_test.jsonl
- redteam.jsonl
- deploy/app.py
- deploy/gateway.py
- deploy/guard.py
- deploy/rag.py
- deploy/Modelfile
- deploy/Modelfile.base
- deploy/policies.md

LICENSE
The code is released under the MIT License (see LICENSE).
Data files that scripts download keep their own licenses.
