This repository provides a curated collection of deep learning tutorials for AI developers, covering essential operations like training, inference, deployment, and application building. It aims to be a central hub for learning and applying AI technologies from the ModelScope community.

How It Works

The tutorials are presented as Jupyter notebooks, offering practical, step-by-step guidance on various AI tasks. The collection emphasizes hands-on experience with popular frameworks and techniques, including Large Language Models (LLMs), diffusion models for image and video generation, and agent-based systems.

Quick Start & Requirements

• Install/Run: Access tutorials via provided links; execution typically requires a Python environment with Jupyter Notebooks and relevant AI libraries.
• Prerequisites: Specific hardware (e.g., GPUs) and software dependencies (e.g., CUDA, specific Python versions, AI frameworks like PyTorch/TensorFlow) will vary per tutorial.
• Resources: Setup time and resource footprint depend on the complexity of the individual tutorial's AI models and tasks.
• Links:
  • RAGFlow: RAGFlow样例
  • Unsloth: unsloth样例
  • LLaMA-Factory: LLaMA-Factory样例
  • Dify: Dify样例
  • vLLM: vLLM样例
  • VLMEvalKit: VLMEvalKit样例
  • Omnigen: Omnigen样例
  • General Training: 古文翻译训练样例
  • Full Dataset Training: 全流程知乎数据集训练
  • LLM Tutorials: LLM-tutorial
  • AIGC Tutorials: AIGC-tutorial

Highlighted Details

• Covers advanced LLM topics like human preference alignment, quantization, and specific models (e.g., OpenAI-O1).
• Includes tutorials on diffusion models for text-to-image and text-to-video generation (DiT, ViViT).
• Features examples for building AI agents using frameworks like AgentFabric.
• Demonstrates practical applications with RAGFlow, Unsloth, and LLaMA-Factory.

Maintenance & Community

• The repository is actively updated with new tutorials and examples, as indicated by recent additions in late 2023 and early 2024.
• Specific community links (Discord/Slack) or contributor details are not provided in the README.

Licensing & Compatibility

• The repository's license is not explicitly stated in the provided README snippet.

Limitations & Caveats

• The README does not specify the project's license, which is crucial for commercial use or integration into closed-source projects.
• Detailed setup instructions and dependency management for each tutorial are not consolidated, requiring users to consult individual notebook requirements.