Fine-tuning & Model Customization

12 lessons in AI Engineering / Working with LLMs

• Dataset Size and QualityFlashcard
• Fine-Tune vs Prompting vs RAGFlashcard
• What is Fine-TuningFlashcard
• Adapters and Prefix/Prompt TuningFlashcard
• DPO and Preference AlignmentFlashcard
• QLoRA and Quantized Fine-TuningFlashcard
• Preparing Training DatasetsFlashcard
• Instruction Fine-Tuning (SFT)Flashcard
• Train/Validation/Test SplitsFlashcard
• LoRA (Low-Rank Adaptation)Flashcard
• RLHFFlashcard
• Full vs Parameter-Efficient Fine-TuningFlashcard