Lordog / dive-into-llms

2024-04-08 · Source: Github Trending: All languages · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Cybersecurity & Data Privacy · Depth: Novice, short

Summary

The "Hands-on Large Models" series, version v0.1.0, offers free programming practice tutorials for large models, extending lecture notes from Shanghai Jiao Tong University courses. Updated on 2025/06/06, it now includes a "Full-Process Large Model Development" public welfare tutorial, developed in collaboration with Huawei Ascend Community, which provides PPTs, lab manuals, and videos. The series covers topics such as fine-tuning and deployment, prompt learning, knowledge editing, mathematical reasoning, model watermarking, jailbreak attacks, large model steganography, multimodal models, GUI agents, agent security, and RLHF safety alignment. This resource aims to help students and researchers quickly grasp large model concepts for course projects or academic research.

Key takeaway

For AI students and machine learning engineers seeking practical experience with large models, explore this tutorial series to gain hands-on skills in areas like fine-tuning, prompt engineering, and model security. Utilize the provided scripts and guides to implement techniques directly, especially the new Huawei Ascend-backed "Full-Process Large Model Development" course for comprehensive learning.

Key insights

This tutorial series provides practical, free resources for large model development and security topics.

Principles

• Practical exercises accelerate large model comprehension.
• Security requires understanding attack vectors.
• Multimodal models enhance real-world simulation.

Method

The tutorial employs a structured approach, offering slides, detailed tutorials, and executable scripts (Jupyter notebooks) for each topic, facilitating hands-on learning and direct application.

In practice

• Fine-tune pre-trained models for specific tasks.
• Implement prompt engineering for better API inference.
• Embed invisible watermarks in generated text.

Topics

• LLM Fine-tuning
• Prompt Engineering
• LLM Security
• Multimodal LLMs
• AI Agents

Code references

• Lordog/dive-into-llms

Best for: AI Student, Machine Learning Engineer, Research Scientist

Related on AIssential

• IEEE Rolls Out Large Language Models Virtual Training Course — Large language models are fundamental architectural components demanding deep technical understanding for reliable and secure integration into digital infrastructures.
• Where can I learn the basic LLMs and local LLMs concepts? — Understanding LLM terminology like quantization, inference, and prompt processing is crucial for new practitioners.
• Providing Greater Access to LLMs with Brandon Duderstadt, Co-Founder and CEO of Nomic AI — Fine-tuning and prompt engineering are crucial for optimizing LLM performance and accessibility.
• Deep Dive into LLMs like ChatGPT — LLMs are trained in stages, from vast internet data to human-guided refinement, enabling complex, yet fallible, capabilities.
• An Open Course on LLMs, Led by Practitioners — Industry veterans offer a free, applied LLM survey course covering evals, RAG, and fine-tuning for technical professionals.
• AI News: This Video Model Has Everyone Freaked Out! — New AI models are pushing boundaries in multimodal video generation, accelerated code synthesis, and cost-effective, agentic LLMs.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Github Trending: All languages.