LOCAL PREVIEW View on GitHub

Fine Tuning Techniques

Notes on Fine Tuning Techniques for ML platform / Applied AI interview preparation. The file index below shows what's in scope; click through to the individual notes for the depth.

Interview talking points

  • This is a sub-topic under Fine-Tuning-Foundational-Models. See the parent for the broader interview framing.

Files in this folder

File Title
04-lora-qlora-llm-customization.md 04. LoRA/QLoRA LLM Customization — Adapting Claude 3.5 Sonnet via Parameter-Efficient Methods
04-lora_qlora_scenarios_mangaassist.md LoRA and QLoRA Scenarios - MangaAssist
11-prompt-tuning-prefix-tuning.md 11. Prompt Tuning and Prefix Tuning — Lightweight Alternatives to LoRA
11-prompt_prefix_tuning_scenarios_mangaassist.md Prompt Tuning and Prefix Tuning Scenarios - MangaAssist
12-quantization-aware-training.md 12. Quantization-Aware Training — INT8/INT4 Without Quality Loss
12-quantization_aware_training_scenarios_mangaassist.md Quantization-Aware Training Scenarios - MangaAssist

Back to the parent.