# wdndev/llm_interview_note

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

Repository: https://github.com/wdndev/llm_interview_note
Canonical: https://ross.abutalabs.com/products/llm_interview_note
Homepage: https://wdndev.github.io/llm_interview_note
Language: HTML
License Family: other
Topics: llm, llms, interview, llm-interview
Last push: 2026-06-14T14:57:07+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 87, release rhythm 35, longevity 73
- inputs: {"age_days": 1029, "days_push": 80, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 14963, forks 1465 (observed 2026-08-28T04:11:09.003621+00:00)

## What it is
A curated Chinese-language study guide and interview question bank covering large language model fundamentals, architectures, training, and application engineering. It is published as an online book with notes on topics like tokenization, attention, decoding strategies, RAG, and MCP.

## Use cases
- prepare for llm algorithm engineer interviews
- study large language model fundamentals and transformer architecture
- review common llm interview questions and answers
- learn about rag, mcp, and prompt engineering concepts
- find a structured llm knowledge roadmap in chinese

## When to choose
- you are preparing for an LLM/algorithm engineer job interview and want a topic-by-topic question bank
- you want a free, structured Chinese-language reference on LLM concepts from tokenization to decoding strategies
- you prefer reading curated notes online rather than assembling resources yourself

## When to avoid
- you need production code or runnable implementations rather than study notes
- you need authoritative, peer-reviewed explanations - answers are self-written and may contain errors
- you need English-language material or formal course-style instruction

## Facets
- artifact type: learning-resource
- maturity: active
- function: documentation, nlp, llm-training, rag, mcp, prompt-engineering
- domain: large-language-models, tutorials, machine-learning, deep-learning
- platform: python
- tags: llm-interview, interview-preparation, study-notes, chinese-language, transformer, llm-engineer, knowledge-base, mkdocs, natural-language-processing, ai-agents, retrieval-augmented-generation, web-server

## Member repositories
- wdndev/llm_interview_note (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:09.003621+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:06:47.696757+00:00, confidence not recorded.
  - readme: https://github.com/wdndev/llm_interview_note (fetched 2026-08-28T04:11:09.003621+00:00, sha 11c2394db351)
  - homepage: https://wdndev.github.io/llm_interview_note (fetched 2026-08-29T08:04:45.761802+00:00, sha 302eb3f03c36)
- Data as of 2026-08-30T08:39:29.467469+00:00.