Files
nexus/wiki/concepts/LLM.md

42 lines
1.0 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
---
id: llm
title: "LLM"
type: concept
tags: [AI, language-model, foundation-model]
sources:
- "[[LLM Terms Framework]]"
last_updated: 2025-12-20
---
## Definition
LLMLarge Language Model大语言模型是参数规模≥1B的深度学习模型能够理解和生成人类语言。
## Core Properties
- **参数规模**通常≥10亿参数
- **语言理解**:能够理解复杂语义
- **文本生成**:能够生成连贯、合法的文本
- **上下文学习**:能从少量示例中学习
## Key Metrics
- **Token**:基本输入单元
- 1英文字符 ≈ 0.3 token
- 1中文字符 ≈ 0.6 token
- **Context Window**:模型能接受的上下文长度
## Related Concepts
- [[Token]]LLM的基本输入单元
- [[MCP]]LLM与外部工具的连接协议
- [[Agent]]LLM+MCP的智能体
- [[RAG]]扩展LLM能力的技术
- [[Embedding]]LLM理解文本的基础
## Connections
- [[LLM]] ← uses ← [[Token]]
- [[LLM]] ← uses ← [[MCP]]
- [[Agent]] ← combines ← [[LLM]] + [[MCP]]
- [[RAG]] ← extends ← [[LLM]]