modelscope/ms-cookbook
魔搭紫皮书|ModelScope Cookbook:面向开发者的开源模型应用实战指南,覆盖模型选型、推理、微调、评测、RAG、Agent 与 AIGC,从跑通第一个模型到构建实际应用。
About the project
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.
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
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 17 stars so far today, about 26 expected by the end of the day.
- The spike has held for 3 days in a row — not a one-off blip.
- The repository is 7 days old and already has 312 stars.
- About 13 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 312
- Stars in a day
- 26
- Forks
- 49
- Issues and pull requests
- 3
- Watchers
- 4
- Language
- HTML
- License
- Apache-2.0
- Created
- September 11, 2026
- Last push
- September 18, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 17, 2026Top new repositories this week: #33
- September 16, 2026Top new repositories this week: #76
Similar projects
-
6.2
AbdelStark/awesome-typesafe
A curated list of official resources and community projects around TypeSafe, System One models, and Jev — an API that returns typed probabilistic decisions instead of generated text.
-
6.0
cobanov/awesome-jev
A curated list of projects built with Jev, TypeSafe AI's System One model for fast typed probabilistic decisions (classification, routing, scoring, guardrails).
-
5.6
dabit3/jev-experiments
A collection of TypeScript demo apps focused on low latency and type safety; each app lives in its own top-level directory with its own README and tests.
-
5.6
theoephraim/awesome-cloudflare-selfhosted
A curated list of open-source apps that replace SaaS products and run in your own Cloudflare account on Workers, D1 and R2. Each entry is audited against its licence and deploy configuration.
-
5.5
yibie/awesome-jev
A curated list of public projects, integrations, and discussions built on Jev — TypeSafe AI's System One model for typed decisions (choice, score, boolean with confidence).
-
5.4
sabbircode-dev/learning-python
A personal repository of learning programs and exercises covering Python basics: variables, conditions, loops, functions and simple projects.