feat: complete wikification of War Commander batch 1&2 and final grey dot cleanup

2026-04-27 18:58:22 +09:00
parent 3424166ea2
commit 6b86b0da4c
2706 changed files with 9074 additions and 7273 deletions
@@ -1,6 +1,6 @@
 ---
 id: P-REINFORCE-AUTO-FITU-001
-category: "[[10_Wiki/💡 Topics/AI]]"
+category: "10_Wiki/💡 Topics/AI"
 confidence_score: 0.98
 tags: [auto-reinforced, fine-tuning, llm, transfer-learning, domain-adaptation, lora]
 last_reinforced: 2026-04-20
@@ -26,6 +26,6 @@ last_reinforced: 2026-04-20
 - **정책 변화(RL Update)**: 단순히 데이터를 넣는 수준을 넘어, 모델의 가치관과 윤리를 정렬하는 RLHF/DPO 정책과 결합되어 '지능의 방향성 정책'을 설정하는 과정으로 고도화됨. (DPO와 연결)

 ## 🔗 지식 연결 (Graph)
- [[Transfer-Learning]], [[DPO (Direct Preference Optimization)]], [[Optimization]], [[Efficiency]], [[Constitutional AI (헌법 AI)]]
+- Transfer-Learning, [[DPO (Direct Preference Optimization)]], [[Optimization]], [[Efficiency]], [[Constitutional AI (헌법 AI)]]
 - **Modern Tech/Tools**: LoRA, QLoRA, Hugging Face `peft` library, Unsloth.
 ---