Hands-on: Teaching a Local 4B Model New Domain Knowledge via CPT+RAG

Author @funJS shares a full hands-on retrospective on using continued pre-training (CPT) to teach a local small model entirely new domain knowledge. The experiment is based on the Qwen 3.5 4B model, uses Unsloth for both CPT and SFT LoRA training, and pairs it with RAG for comparison, with evaluation results provided throughout.

Confirmed

Why it matters

2026-09-25 ~ 2026-09-25 · 5 related posts

Primary sources

3 near-duplicate retellings: funJS · funJS · funJS