---
id: wiki-2026-0508-sft-supervised-fine-tuning
title: SFT (Supervised Fine-Tuning)
category: 10_Wiki/Topics
status: duplicate
canonical_id: fine-tuning
duplicate_of: "[[Fine-tuning]]"
aliases: [Supervised Fine-Tuning, Instruction Tuning]
source_trust_level: A
confidence_score: 0.9
verification_status: redirected
tags: [duplicate, sft, fine-tuning, llm]
last_reinforced: 2026-05-10
github_commit: pending
---

# SFT (Supervised Fine-Tuning)

> **이 문서는 [[Fine-tuning]] 의 중복본입니다.** Canonical 문서로 redirect.

## 핵심 요약 (SFT-specific aspects)
- SFT = supervised stage of LLM post-training (prompt → response pairs).
- 매 RLHF/DPO pipeline 의 첫 stage — base model → instruction-following model.
- 일반적 dataset: ShareGPT, OpenAssistant, Alpaca-style, custom domain Q&A.
- 매 2026 typical recipe: LoRA/QLoRA on Llama 3.x / Qwen 2.5 + 1-3 epochs at ~2e-5 LR.
- 후속 stage: DPO → KTO → online RL (GRPO).

## 🔗 Graph
- 부모: [[Fine-tuning]] (canonical)
- Adjacent: [[RLHF]] · [[DPO]] · [[LoRA]] · [[Instruction-Tuning]]

## 🕓 변경 이력
| 날짜 | 변경 |
|---|---|
| 2026-05-08 | Phase 1 |
| 2026-05-10 | 중복 처리 — canonical 문서로 redirect |