Solo project, sharing it here for the AI angle rather than the subject matter. I fine-tuned Llama 3.1 8B (QLoRA, single T4) on the complete works of a 19th-century author whose corpus is fully public domain. The interesting problem wasn't the domain — it was trying to get a small model to cite its source (book, chapter, item) on every answer instead of just asserting things confidently. What I learned, which might be useful to others doing domain fine-tunes: - Teaching the *format* of cita...