docs: 벤치마크 섹션 한국어로 변환

docs: add Korean LLM benchmark results (KMMLU + HAE-RAE, 3-model comparison)

docs: add llama-cpp-python, vllm, ollama tags for library discovery

docs: add MLX 4-bit format, update quant links in model card

docs: update README to v1.3 (DPO v6)

Update README.md

docs: add recommended inference settings and backend configuration guide

docs: add GitHub framework link and badges

Update README.md

docs: add real output example (RT + Quick Assessment + Analysis Report)

docs: update model card with v3 training data (58K SFT, 26K DPO), MLX benchmark, Markdown RT format

docs: update training data distribution with accurate numbers (SFT 36,713 + DPO 24,779)

docs: update model card with GGUF formats, benchmarks, usage examples

Fix year to 2026

Update model card for DPO v4

initial commit