CtrlK

📃前言
🎚️基础部分
🦖Transformer
Prompt Engineering
- Tree of Thoughts
LLM应用
- RAG
  - Graph RAG
Linear Algebra
🎄模型训练
- LLM显存需求
  - LLM精度问题
  - LLM训练需要多少显存
🐒MoE
- 专家并行

Powered by GitBook

On this page

🦖Transformer

Tokenizer Embeddings Positional Encoding Self Attention Multi-Head Attention Add & Norm FeedForward Linear & Softmax Decoding Strategy

PreviousLLM基础 NextTokenizer