Hugging Face 的設計哲學：為什麼我們反其道而行，選擇「重複程式碼」？
Original: ~Don't~ Repeat Yourself
This classic blog post from Hugging Face examines the tension between software engineering principles and the demands of machine learning…
Hugging Face 探討了其開源庫 Transformers 的核心設計哲學。與傳統軟體工程極力避免重複程式碼（DRY 原則）不同，他們選擇了「重複自己」的「單一檔案政策」（Single-file policy）。這種設計讓每個模型（如 BERT、GPT）的程式碼都獨立完整，極大地提升了機器學習研究者的閱讀與修改效率，雖然增加了維護重複程式碼的成本，但換來了極高的靈活性。
This classic blog post from Hugging Face examines the tension between software engineering principles and the demands of machine learning (ML) research, revealing the core design philosophy behind the `transformers` library.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Hugging Face Blog →Summaries are AI-generated; the original article is authoritative.