28 lines
1.1 KiB
Markdown
28 lines
1.1 KiB
Markdown
---
|
||
title: "Large Language Model"
|
||
type: concept
|
||
tags: [llm, nlp, deep-learning]
|
||
aliases: [LLM, 大语言模型, Large Language Model]
|
||
last_updated: 2025-12-20
|
||
---
|
||
|
||
## Definition
|
||
Large Language Model，大语言模型。行业通常以参数规模和训练数据/算力来衡量是否称为"大模型"，语言模型常在 ≥1B 参数开始被称为"大模型"。
|
||
|
||
## Key Facts
|
||
- 1B = Billion = 10亿参数
|
||
- 常见大模型示例：GPT-2（1.5B）、GPT-3（175B）、GPT-4（参数量未公开）
|
||
- 参数规模是衡量模型能力的重要指标之一
|
||
|
||
## Connections
|
||
- [[Agent]] ← 构建于 ← [[Large Language Model]]
|
||
- [[Prompt]] ← 输入给 ← [[Large Language Model]]
|
||
- [[Model Context Protocol]] ← 连接 ← [[Large Language Model]]
|
||
- [[RAG]] ← 增强 ← [[Large Language Model]]
|
||
- [[vLLM]] ← 加速推理 ← [[Large Language Model]]
|
||
- [[Hallucination]] ← 问题 ← [[Large Language Model]]
|
||
- [[Data Distillation]] ← 蒸馏对象 ← [[Large Language Model]]
|
||
|
||
## Sources
|
||
- [[大模型相关术语和框架总结｜llm-mcp-prompt-rag-vllm-token-数据蒸馏]]
|