# 大语言模型

- [大模型理论](/main/llm/da-mo-xing-li-lun.md)
- [Scaling Law](/main/llm/da-mo-xing-li-lun/scaling-law.md)
- [The Bitter Lesson](/main/llm/da-mo-xing-li-lun/the-bitter-lesson.md)
- [思考，快与慢](/main/llm/da-mo-xing-li-lun/si-kao-kuai-yu-man.md)
- [模型结构](/main/llm/mo-xing-jie-gou.md)
- [MLP](/main/llm/mo-xing-jie-gou/mlp.md): MLP线性
- [Rotary Embedding](/main/llm/mo-xing-jie-gou/rotary-embedding.md)
- [RMSNorm](/main/llm/mo-xing-jie-gou/rmsnorm.md): RMSNorm
- [Encoder-decoder](/main/llm/mo-xing-jie-gou/encoder-decoder.md)
- [Decoder-only](/main/llm/mo-xing-jie-gou/decoder-only.md)
- [MOE](/main/llm/mo-xing-jie-gou/moe.md)
- [常见大模型](/main/llm/mo-xing-jie-gou/chang-jian-da-mo-xing.md)
- [T5](/main/llm/mo-xing-jie-gou/chang-jian-da-mo-xing/t5.md)
- [GPT2](/main/llm/mo-xing-jie-gou/chang-jian-da-mo-xing/gpt2.md)
- [LLaMA](/main/llm/mo-xing-jie-gou/chang-jian-da-mo-xing/llama.md): LLaMA
- [LLaMA 2](/main/llm/mo-xing-jie-gou/chang-jian-da-mo-xing/llama-2.md)
- [Mistral](/main/llm/mo-xing-jie-gou/chang-jian-da-mo-xing/mistral.md)
- [GLM](/main/llm/mo-xing-jie-gou/chang-jian-da-mo-xing/glm.md)
- [Mixture](/main/llm/mo-xing-jie-gou/chang-jian-da-mo-xing/mixture.md)
- [如何训练一个ChatGPT](/main/llm/ru-he-xun-lian-yi-ge-chatgpt.md)
- [微调](/main/llm/wei-tiao.md)
- [Instruction Tuning 指令微调](/main/llm/wei-tiao/instruction-tuning-zhi-ling-wei-tiao.md)
- [Domain Finetune 领域微调](/main/llm/wei-tiao/domain-finetune-ling-yu-wei-tiao.md)
- [解码](/main/llm/jie-ma.md)
- [温度采样](/main/llm/jie-ma/wen-du-cai-yang.md)
- [Beam Search Decoding](/main/llm/jie-ma/beam-search-decoding.md)