Open Source · Interactive · Free Forever

Understand How Large Language Models Think

No math PhD needed. Interactive 3D visualizations make complex LLM concepts intuitive.

15+ free lessons from tokenization to speculative decoding. Click, explore, and learn at your own pace.

Start from Scratch
Explore Modules

Your Learning Journey

Follow the recommended order, or jump to any topic

1 Start Here
✂️
Tokenization
分词器

Understand BPE, WordPiece, and SentencePiece — how text becomes tokens for LLMs.

2
📐
Embedding
嵌入层

Visualize how tokens become vectors in high-dimensional space and why similarity matters.

3
🔄
Transformer Architecture
Transformer 架构

Explore the complete Transformer architecture in 3D — Encoder, Decoder, Attention, and data flow.

4
👁️
Attention Variants
注意力变体

Multi-Head, Grouped Query, Sliding Window, and Flash Attention — the evolution of attention.

5
KV Cache
KV 缓存

How KV caching accelerates autoregressive inference and the PagedAttention optimization.

6
🏋️
Training Pipeline
训练流程

Pre-training, supervised fine-tuning, and the complete training loop with loss landscapes.

7
🔧
LoRA
LoRA 微调

Low-Rank Adaptation — efficient parameter-efficient fine-tuning for large models.

8
🎯
RLHF
RLHF 对齐

Reinforcement Learning from Human Feedback — aligning LLMs with human preferences.

9
📚
RAG
检索增强生成

Retrieval-Augmented Generation — grounding LLM outputs in external knowledge sources.

10
🧠
Mixture of Experts
混合专家

Sparse expert routing — how Mixtral, DeepSeek & GPT-4 scale to huge capacity with constant per-token compute.

11
🗜️
Quantization
量化

FP32, INT8, INT4 & GGUF — how low-bit quantization shrinks models 4-8× to run on a single GPU.

Interactive Tools

Free calculators and side-by-side comparisons — bookmark these and come back whenever you need them.

Go Deeper

Frontier techniques from recent research papers, illustrated in 3D. For readers who've mastered the fundamentals — or anyone curious about what's next.

View all articles →