Page 3 - Showing 4 of 20 posts
View all posts by years →
- QLoRA Made Fine-Tuning Feel Practical
How LoRA and QLoRA changed the economics of adapting LLMs.
8 min - RAG Became the Default LLM Pattern
The practical retrieval patterns that made LLM apps useful with private data.
8 min - Instruction Tuning and RLHF Explained
A practical guide to why chat models followed instructions better than base LLMs.
8 min - Open-Weight LLMs Changed the Stack
How LLaMA, Alpaca, Vicuna, and Mistral shifted LLM development.
7 min