Vibe Coding Discoverms-cookbook
View on GitHub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。
ModelScope Cookbook is an open-source, hands-on book (34 chapters) for building real AI applications with open-source models: model selection, inference, fine-tuning, evaluation, RAG, Agents, MCP and AIGC, with runnable examples using ms-swift, EvalScope, DiffSynth and Ollama.
Use Cases
Learn open-source model selection and evaluationRun a first local LLM inference with OllamaFine-tune models with ms-swift on custom dataBuild a RAG enterprise knowledge assistantCreate an MCP tool-connected agentTrain image LoRA with DiffSynthGenerate and edit product marketing imagesBuild a speech assistant with ASR/TTSAnalyze customer-service call qualityEvaluate models with EvalScope baselinesStudy agent frameworks and skillsQuantize models to fit limited hardware
Built With
- Language
- HTML
- Frameworks
- ModelScope · ms-swift · EvalScope · DiffSynth · Ollama · FastAPI · Claude Code · DeepSeek Harness · MiniMax H3
Tags
cookbook · tutorials · llm · fine-tuning · rag · ai-agents · mcp · model-evaluation · aigc · diffusion-models · quantization · modelscope · learning-resource · developer-guide · inference