> For the complete documentation index, see [llms.txt](https://bbb-fullstack-aier.gitbook.io/all-about-llm/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://bbb-fullstack-aier.gitbook.io/all-about-llm/readme.md).

# Summary

[项目github](https://github.com/babytreemi/all-about-llm)

## ❤️ What‘s NEW？

* [ACL2023 Tutorial 关于检索增强型大语言模型以及应用](/all-about-llm/tototolearn/tutorial-and-workshop/acl2023-retrieval-lm.md)
* [baichuan系列模型总结](/all-about-llm/tototolearn/openllm/bai-chuan-da-mo-xing.md)
* [Personality Traits in Large Language Models (Google DeepMind)](/all-about-llm/tototolearn/personality-traits-and-bias-in-llm/personality-traits-in-large-language-models.md)

## 👂🏻屯一些还要整理和入手的repo等

### Baichuan-13B 和 LLaMA2-13B 中文sft

<https://huggingface.co/hiyouga/baichuan-13b-sft> <https://huggingface.co/hiyouga/Llama-2-Chinese-13b-chat>

复现教程↑ <https://zhuanlan.zhihu.com/p/645010851>

相关git：

\[1] ChatGLM-6B, ChatGLM2-6B 微调：[https://github.com/hiyouga/ChatGLM-Efficient-Tuning](<https://github.com/hiyouga/ChatGLM-Efficient-Tuning >)&#x20;

\[2] LLaMA, LLaMA-2, BLOOM, Falcon, Baichuan, InternLM 微调: [https://github.com/hiyouga/LLaMA-Efficient-Tuning ](<https://github.com/hiyouga/LLaMA-Efficient-Tuning >)

\[3] 大模型知识编辑工具：<https://github.com/hiyouga/FastEdit>

### Firefly(流萤): 中文对话式大语言模型

repo： [https://github.com/yangjianxin1/Firefly](<https://github.com/yangjianxin1/Firefly&#xD;&#xA;&#xD;&#xA;>)

<mark style="background-color:red;">可以在16G显存上微调130亿的大模型，</mark>并且这套训练流程在Open LLM排行榜🤗上进行了验证，**比vicuna-13b-1.1略高0.2分，比llams-2-13b-chat略低0.5分**。

post：<https://mp.weixin.qq.com/s/KsbgRNTwXE86kCGTJhu0WQ>

3D-LLM：将 3D 世界注入大型语言模型：<https://github.com/UMass-Foundation-Model/3D-LLM>

### LIMA: Less Is More for Alignment, by Meta AI[&#xD;&#x20;&#xD;<br>](<https://github.com/yangjianxin1/Firefly&#xD;&#xA;&#xD;&#xA;>)