Large Language Model (LLM) Zone
A comprehensive LLM beginner's guide covering principles, multimodal, applications, deployment, training, architecture, etc., suitable for AI developers and learners.
大模型LLMAI
Translated from Chinese by AI. Spotted an issue? Use the feedback button.
- The Document is All You Need! A One-Stop Beginner's Guide to LLM Core Technology Principles
- Based on Multimodal Large Language Models
- Development: Current Status and Thoughts on Commercializing LLM Applications
- Empower Yourself with Magic – Using LLMs to Assist with Paper Learning
- [Application Example] Deploy Google Gemma Locally
- A Good Cook Still Needs Good Ingredients: How to Prepare Data for LLMs? A Down-to-Earth Summary of Lessons Learned
- Understanding Transformers in One Article: The Core Architecture and Principles of Deep Learning Models
- When Should You Use Chain of Thought (CoT)? – Zhihu
- Fast and Slow Thinking in LLMs: Adapting Your Own LLM Use Cases II – Running Flux on Mac/Edge Devices and WeChat
- Yun Shu: Using Claude to Create Four-Panel Comics, Explaining Claude's Latest Paper – An Intuitive Understanding of LLM Principles (with Exclusive Comic Prompts)
- Deploy InternLM's Latest Multimodal Model InternVL3 Locally (Supports RTX 50 Series GPUs)
- What You Didn't Know About LLM Training: Principles, Pathways, and New Practices
- Mixture of Experts (MoE) Architecture Explained
- Why Long-Term Memory in LLMs Remains an Unsolved Problem
- A Detailed Explanation of Prompt Caching Techniques in Large Language Models
- How LLM Inference Works
- 2026 LLM Engineering Roadmap (with Free Open-Source Learning Resources)
- How to Build Your Own LLM from Scratch: The Complete 5-Stage Process Behind GPT and Claude