# km1994/LLMsNineStoryDemonTower

【LLMs九层妖塔】分享 LLMs在自然语言处理（ChatGLM、Chinese-LLaMA-Alpaca、小羊驼 Vicuna、LLaMA、GPT4ALL等）、信息检索（langchain）、语言合成、语言识别、多模态等领域（Stable Diffusion、MiniGPT-4、VisualGLM-6B、Ziya-Visual等）等 实战与经验。

Repository: https://github.com/km1994/LLMsNineStoryDemonTower
Canonical: https://ross.abutalabs.com/products/llmsninestorydemontower
License Family: other
Last push: 2024-03-30T15:08:33+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 87
- inputs: {"age_days": 1221, "days_push": 886, "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 2168, forks 205 (observed 2026-08-28T04:06:21.505744+00:00)

## What it is
A curated Chinese-language tutorial collection ('Nine-Story Demon Tower') covering hands-on practice with open-source LLMs such as ChatGLM, LLaMA, Vicuna, and Baichuan, plus PEFT fine-tuning, LangChain, Stable Diffusion, multimodal VQA models, ASR, and TTS. It organizes guides, experience notes, and interview material for practitioners getting started with large language models.

## Use cases
- learn how to run and fine-tune ChatGLM or Chinese-LLaMA locally
- find tutorials for parameter-efficient fine-tuning like QLoRA
- get started with LangChain for retrieval and knowledge extraction
- explore text-to-image and visual question answering models like MiniGPT-4
- learn speech recognition and text-to-speech with Whisper and MMS
- prepare for LLM-related interviews
- compare open-source Chinese LLM derivatives

## When to choose
- you want curated Chinese-language tutorials and practical notes on open-source LLMs
- you need a broad survey of LLM, multimodal, and speech tooling in one place
- you are a beginner looking for guided entry points into the LLM ecosystem

## When to avoid
- you need production-ready software rather than tutorials and links
- you require up-to-date coverage of the newest models, as the collection is a static snapshot
- you need English-language documentation

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: llm-inference, llm-training, rag, speech-recognition, tts, stable-diffusion, prompt-engineering
- domain: large-language-models, speech-processing, image-processing, tutorials, awesome-lists
- platform: python, cross-platform
- tags: llm-tutorials, chinese-llms, fine-tuning, multimodal, curated-list, hands-on-guides, natural-language-processing, retrieval-augmented-generation

## Member repositories
- km1994/LLMsNineStoryDemonTower (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:21.505744+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 2026-08-30T02:49:30.467148+00:00, confidence not recorded.
  - readme: https://github.com/km1994/LLMsNineStoryDemonTower (fetched 2026-08-28T04:06:21.505744+00:00, sha c112fbfc7532)
- Data as of 2026-08-30T08:39:29.467469+00:00.