Train Your Own LLM - companion code
Chapter 17: Capstone: A Small, Fast Classifier and Extractor

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
pip install sentence-transformers==6.1.0 scikit-learn==1.9.1
Run get_data.sh first: it downloads the Banking77 CSVs (train.csv, test.csv,
categories.json) that b77.py reads.

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
- b77.py
- categories.json
- ch17_confusions.py
- ch17_embed_lr.py
- ch17_extract.py
- ch17_finetune.py
- ch17_how_many.py
- ch17_prompt.py
- shop_json_train.jsonl
- shop_json_test.jsonl
- shop_messy_test.jsonl
- get_data.sh

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