From 645299fe7cf6f701fb00f82a91c42755181adc1a Mon Sep 17 00:00:00 2001 From: medusa Date: Sat, 30 Mar 2024 05:03:50 +0000 Subject: [PATCH] Add docs/tech_docs/llm/llm_visuals.md --- docs/tech_docs/llm/llm_visuals.md | 70 +++++++++++++++++++++++++++++++ 1 file changed, 70 insertions(+) create mode 100644 docs/tech_docs/llm/llm_visuals.md diff --git a/docs/tech_docs/llm/llm_visuals.md b/docs/tech_docs/llm/llm_visuals.md new file mode 100644 index 0000000..8afb94b --- /dev/null +++ b/docs/tech_docs/llm/llm_visuals.md @@ -0,0 +1,70 @@ + +## `Claude` + +```mermaid +graph TD + A[Input Text] --> B[Tokenization] + B --> C[Embedding] + C --> D[Transformer Encoder] + D --> E[Transformer Decoder] + E --> F[Output Text] + + subgraph Transformer + D[Transformer Encoder] + E[Transformer Decoder] + end + + subgraph Attention Mechanism + G[Multi-Head Attention] + H[Feed Forward] + I[Add & Norm] + end + + D --> G + G --> H + H --> I + I --> D + I --> E + + classDef input fill:#f9f,stroke:#333,stroke-width:4px + classDef output fill:#9ff,stroke:#333,stroke-width:4px + classDef transformer fill:#ff9,stroke:#333,stroke-width:2px + classDef attention fill:#f90,stroke:#333,stroke-width:2px + + class A input + class F output + class Transformer transformer + class Attention Mechanism attention +``` + +> zeroshot + +--- + +## `ChatGPT` + +### Graph 1 + +```mermaid +graph TD; + A[Input Layer: Text Tokens] --> B[Embedding Layer]; + B --> C[Transformer Block 1]; + C --> D[Transformer Block 2]; + D --> E[...]; + E --> F[Transformer Block N]; + F --> G[Output Layer: Predicted Next Token]; +``` +## Graph 2 + +```mermaid +graph TD; + A[Input from Previous Layer] --> B[Self-Attention Mechanism]; + B --> C[Add & Normalize]; + C --> D[Feed-Forward Neural Network]; + D --> E[Add & Normalize]; + E --> F[Output to Next Layer]; + A -->|Skip Connection| C; + C -->|Skip Connection| E; +``` + +> zeroshot \ No newline at end of file