Open Documentation
Fine-Tuning Cookbooks
& Engineering Guides
A growing repository of utility scripts, bug fixes, tutorials, and architectural frameworks to support the community navigating model fine-tuning and agentic deployments.
RAG vs. Fine-Tuning: When to use which
A technical framework for deciding between RAG for dynamic knowledge retrieval and SFT for behavioral logic.
ArchitectureRAGSFTSystem Design
What is the Model Context Protocol?
A technical guide to MCP architecture, how it solves the M x N integration problem, and when to use it for deterministic tool calling.
ArchitectureAgentsAnthropicMCP
How to Train Custom Tokens with LoRA
Fix untrained embedding errors and prevent model gibberish when adding custom tokens to a vocabulary during PEFT fine-tuning.
Bug FixLoRAPEFTTokenization
PEFT Explained: LoRA vs. QLoRA
A deep dive into Parameter-Efficient Fine-Tuning. Learn how LoRA rank matrices and QLoRA 4-bit quantization affect VRAM and training speed.
ArchitectureLoRAQLoRAPEFT