# datawhalechina/so-large-lm

大模型基础: 一文了解大模型基础知识

Repository: https://github.com/datawhalechina/so-large-lm
Canonical: https://ross.abutalabs.com/products/so-large-lm
Homepage: https://datawhalechina.github.io/so-large-lm
License Family: other
Last push: 2026-06-22T02:15:28+00:00

## Health v2 (maintenance only)
Score: 68/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 88, release rhythm 35, longevity 81
- inputs: {"age_days": 1143, "days_push": 73, "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 7605, forks 632 (observed 2026-08-28T04:10:01.990886+00:00)

## What it is
An open-source Chinese-language tutorial series on large language model fundamentals, based on Stanford CS324 and Hung-yi Lee's generative AI course. It covers the full LLM pipeline from data engineering and Transformer architecture to training, evaluation, safety, and ethics.

## Use cases
- learn large language model fundamentals
- understand transformer architecture and attention mechanisms
- study LLM training and data engineering
- learn about MoE and retrieval-based model architectures
- find a structured LLM learning path in Chinese
- prepare for LLM research or engineering work

## When to choose
- you want a free, systematic, theory-first introduction to LLMs
- you prefer Chinese-language learning materials with video companions
- you want curated links to Stanford CS324-style content

## When to avoid
- you need hands-on code for deploying or fine-tuning models (use self-llm or llm-universe instead)
- you need a software library or tool rather than a tutorial
- you need English-only materials

## Facets
- artifact type: learning-resource
- maturity: active
- function: documentation, llm-training, machine-learning
- domain: large-language-models, deep-learning, tutorials, education
- platform: -
- tags: llm-tutorial, chinese-language, open-course, transformer, datawhale, web-server

## Member repositories
- datawhalechina/so-large-lm (main) score 68

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:01.990886+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 2026-08-29T17:36:51.076397+00:00, confidence not recorded.
  - readme: https://github.com/datawhalechina/so-large-lm (fetched 2026-08-28T04:10:01.990886+00:00, sha 911417a485d1)
  - homepage: https://datawhalechina.github.io/so-large-lm (fetched 2026-08-29T08:32:25.327592+00:00, sha 81f3b8170f7e)
- Data as of 2026-08-30T08:39:29.467469+00:00.