# modelscope/ms-cookbook > ModelScope Cookbook is an open-source hands-on guide to building real applications with open-source AI models: model selection, inference, data prep, fine-tuning, evaluation, RAG, Agents, and AIGC. 8 parts and 34 chapters with runnable examples using EvalScope, ms-swift, DiffSynth, and Ollama. - Magnitude: 0.2 out of 10 — Cooling - Stars: 397 total · +0 stars on 2026-09-28 (UTC), ≈ 0 by evening - Star trust: star growth looks organic - Category: Learning & lists · Language: HTML · License: Apache-2.0 · Created: 2026-09-11 · Last push: 2026-09-21 - GitHub: https://github.com/modelscope/ms-cookbook · Homepage: https://modelscope.cn/active/ms-cookbook · Page: https://gitnova.dev/en/r/modelscope/ms-cookbook ## Useful for - Run a first inference of an open-source model following chapter 07 - Fine-tune a model on your own data with ms-swift via chapters 12-13 - Build a RAG assistant over an enterprise knowledge base from chapter 19 ## Why it’s here - The repository is 17 days old and already has 397 stars. ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 72 - Issues and pull requests: 7 - Watchers: 6 - Average over the last week: 2 per day - Usual pace: 27 per day ## Stars per day, last 30 days (oldest → newest, today is partial) 2026-10-04 … 2026-11-02: None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None ## Magnitude by day, last 13 days 09-16 5.5, 09-17 6.1, 09-18 4.6, 09-19 3.2, 09-20 2.9, 09-21 2.6, 09-22 1.9, 09-23 1.3, 09-24 1.1, 09-25 0.7, 09-26 0.4, 09-27 0.5, 09-28 0.2 --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-09-28 00:05 UTC, updated every 30 minutes.