Funes者，以Git为基之框架也，化原始之源为持久引据之智业，有AI之馆吏焉。
藏書之役，納其本源，永錄不變，編為互鏈之Markdown維基，復以維基成引文之答、報、析、程、他可再用之物。汝供其源與問，此役處其撰、鏈、索、檢、維。
万物皆存于素朴之Markdown于Git仓库之中，故尔知识库得版本化，可较，可携，可索，且于GitHub或任一编辑器中可用.
此流程化用Andrej Karpathy之“LLM知识库”意于素朴之Git仓库，非Obsidian.
名之由
Funes以博尔赫斯之“福内斯记性人“其人能忆万般，然不能悟其理。”
此项目存其本真之记，复析之而为理、为题、为可用之效。
其运作之道如何
raw source ─ingest→ raw/ (verbatim, immutable)
─compile→ wiki/sources/ (one summary note per source)
→ wiki/concepts/ (atomic articles, one idea each)
→ wiki/topics/ (maps of related concepts)
question ─answer→ read wiki, cite articles
─output→ outputs/ (reports, analyses, routines, answers)
→ wiki/ (durable findings filed back in)
此维基非终成之产也。乃馆者应问、成报、制程、察缺、维知库之脉络久远所凭之记也。
尔鲜手改维基。尔供源与问；馆者持其构、联、索、出。
此乃例库之显也。 可浏览以见冯斯之输出若何。
速启之
-
以此仓库为模板 用 GitHub 之“以此模板”按钮，或克隆之。
-
以能动编程之器启之 如 Claude Code、Codex，或任何能读而编辑仓库中文件之 LLM 之器。此器读
AGENTS.md。 -
增援文献。将PDF、网页摘录、笔记或他物投于
starter-library/raw/，言曰：纳新文献于
raw/。或直贴文辞或链接于言谈，言曰：
纳此
-
。询诸事。 藏书者引据于维基，著述宏论于
outputs/，且愿将恒久之得录于知识库. -
务使其康健. 时而询以“体魄检视”，以核断链、重概念、陈索引、矛盾、缺漏及新篇之可能.
更名或摹写starter-library/ 以适君之题，如 physics/、history/、research/ 或 personal-kb/。欲于一库中运行数独立知识库，当增置顶层库名。详 library.md。
此中何物
starter-library/— 一已备之空知识库，具标准raw / wiki / outputs / meta框架及种子索引之文。AGENTS.md— 众工之入口也：各匣所存何物，及于此库如何措手.protocol.md— 共用之典籍之约：自全录而编次，至审察而后成文，复经检校，终成章句，并其常规与文式之范.&A — 输出而后察其康健.library.md— 同此库增列新典之方.
例 — 典籍之成文者何如也
此非手书。此显编译之维基形貌。全模存于protocol.md。
一源注，总括原源，并系其所养之理：
--- title: Attention Is All You Need type: source tags: [transformers, attention] created: 2026-01-10 updated: 2026-01-10 --- # Attention Is All You Need - **Raw file:** [2026-01-10-attention-is-all-you-need.pdf](../../raw/2026-01-10-attention-is-all-you-need.pdf) - **Original:** https://arxiv.org/abs/1706.03762 ## Summary Introduces the Transformer, a sequence model based entirely on attention, dropping recurrence and convolution. ## Key takeaways - Self-attention relates all positions in a sequence in O(1) sequential steps. - Multi-head attention lets the model attend to different subspaces at once. ## Concepts extracted - [Self-attention](../concepts/self-attention.md) - [Multi-head attention](../concepts/multi-head-attention.md)
一原子之理，释一义理，复系其源，相联之理，及题目之图。
--- title: Self-attention type: concept tags: [transformers] created: 2026-01-10 updated: 2026-01-10 --- # Self-attention A mechanism that computes a representation of a sequence by relating each position to every other position, weighting them by learned compatibility. ## Related - [Multi-head attention](./multi-head-attention.md) ## Sources - [Attention Is All You Need](../sources/attention-is-all-you-need.md) ## Topics - [Transformer architecture](../topics/transformer-architecture.md)
之出者，乃出於維基之宏文，或答、或報、或常、或析，皆為豐富之作也。
# Reading plan for understanding Transformers This plan draws on the compiled notes for [Attention Is All You Need](../wiki/sources/attention-is-all-you-need.md), [Self-attention](../wiki/concepts/self-attention.md), and [Multi-head attention](../wiki/concepts/multi-head-attention.md). ## Goal Understand why the Transformer replaced recurrence for many sequence-modeling tasks. ## Sequence 1. Read the source note for *Attention Is All You Need*. 2. Review the concept article on self-attention. 3. Review multi-head attention. 4. Compare the topic map on Transformer architecture against the original paper. ## Durable findings to file back - Add a concept article on positional encoding. - Add a topic map for sequence modeling.
之謝
，其式仿自安德烈·卡帕西之《大語言模型知識庫》。至於建一自進之克勞德知識庫之說，則源於系統改良之師。