peft 5
- Prompting, RAG, or Fine-Tuning: An Architectural Decision Matrix for LLM Adaptation
- Parameter-Efficient Fine-Tuning: Architectural Mechanics of LoRA, QLoRA, and Variants
- LoRA vs Frontier Models: When Specialized 7B Adapters Outperform GPT-4
- LLaMA-Factory Architecture: Unified Post-Training Across 100+ LLMs
- Hugging Face Cookbook: Practical Open-Source AI Architecture and Deployment Patterns