# echonoshy/cgft-llm

Practice to LLM.

Repository: https://github.com/echonoshy/cgft-llm
Canonical: https://ross.abutalabs.com/products/cgft-llm
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2026-05-11T03:25:40+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 81, release rhythm 35, longevity 59
- inputs: {"age_days": 833, "days_push": 114, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2663, forks 342 (observed 2026-08-28T04:07:08.757645+00:00)

## What it is
A hands-on tutorial series (in Chinese) for learning large language model technologies, with Jupyter Notebook code, written docs, and video lessons covering fine-tuning, RAG, agents, MCP, vector databases, and LLM deployment. It is a practice-oriented educational repository rather than a production software library.

## Use cases
- learn how to fine-tune an LLM like deepseek-r1
- build a RAG knowledge base from scratch
- understand tool calling and implement a browser-use agent
- set up an MCP server and client with fastmcp
- monitor LLM services with langfuse
- practice using a vector database like milvus
- design and build an agent system with memory and context

## When to choose
- you want guided, hands-on practice with LLM fine-tuning, RAG, and agents
- you prefer learning through notebooks paired with video walkthroughs
- you want Chinese-language tutorials on modern LLM engineering topics

## When to avoid
- you need a production-ready library or framework to ship in an application
- you want English-language documentation
- you need a single cohesive tool rather than a collection of independent lesson projects

## Facets
- artifact type: learning-resource
- maturity: active
- function: llm-training, rag, agent-framework, mcp, machine-learning, llm-inference
- domain: large-language-models, artificial-intelligence, tutorials
- platform: python, cross-platform
- tags: hands-on-llm, jupyter-notebooks, video-tutorials, fine-tuning, chinese-language, practice-series, ai-agents, retrieval-augmented-generation

## Member repositories
- echonoshy/cgft-llm (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:08.757645+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 2026-08-30T02:18:20.216704+00:00, confidence not recorded.
  - readme: https://github.com/echonoshy/cgft-llm (fetched 2026-08-28T04:07:08.757645+00:00, sha 9ef43a16872e)
- Data as of 2026-08-30T08:39:29.467469+00:00.