-
Notifications
You must be signed in to change notification settings - Fork 54
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
3 changed files
with
56 additions
and
11 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -4,27 +4,52 @@ | |
|
||
Tips: 图片完全由AI生成 | ||
## 🌟 项目简介 | ||
欢迎来到 LLM-Dojo,这里是专为中国初学者设计的修炼道场。!"Dojo"一词借用了其在武术训练中的寓意,象征着一个专注于学习和实践的场所。 | ||
欢迎来到 LLM-Dojo,这里是一个开源大模型学习场所(最好的学习永远在项目中),包括一个开源大模型训练框架,以及llm_tricks模块,其中包括各种大模型的tricks实现与原理讲解! | ||
|
||
在这里,我们将"Dojo"视为一个虚拟的修炼道场,通过LLM Dojo,我们希望建立一个充满活力的社区,让每个人都能在LLM技术的修炼之路上不断进步,最终达到技术的巅峰。 | ||
## 📖 项目目标 | ||
- 提供全面的开源大模型教程,包括但不限于环境配置、本地部署、高效微调等。 | ||
- 简化工作流程:我们的目标是让开源大模型的部署、使用和应用过程变得更加轻松愉悦,使其更易于被更广泛的用户群体接纳。 | ||
- 促进开源精神,鼓励社区参与,共同维护和完善项目。 | ||
## 📊 项目规划及进展 | ||
"Dojo"一词借用了其在武术训练中的寓意,象征着一个专注于学习和实践的场所。 | ||
|
||
在这里,我们将"Dojo"视为一个虚拟的修炼道场,通过LLM Dojo,希望建立一个充满活力的学习场所,让每个人都能在LLM上进行各种训练及Tricks实现。 | ||
## 📖 Latest News | ||
- [2024-04-28] 🚀 更新dora微调原理示例、支持qwen模型微调 | ||
<details> <summary>More news...</summary> | ||
待更新 | ||
</details> | ||
|
||
## 📊 项目规划及进展 | ||
|
||
### 已支持模型 | ||
- [Qwen](https://github.com/QwenLM/Qwen.git) | ||
- [x] [QWEN Lora微调] | ||
|
||
### 已支持tricks及原理讲解 | ||
所有相关的trciks及讲解都在llm_tricks文件夹下 | ||
- Dora | ||
|
||
## 🤓Quick Start | ||
不同的微调方法有不同的配置,但大体都是类似的。常规的参数在utils下的args.py。 | ||
|
||
相关训练参数在train_args文件夹下对应的模型中。 | ||
均是采用dataclass格式配置参数,直接在default中修改即可,即不需要直接命令行传输参数了(如果有小伙伴需要这种方式也可以补上)。 | ||
|
||
设置好相关配置后即可运行main_train.py进行训练 | ||
```sh | ||
python main_train.py | ||
``` | ||
|
||
## 😮训练数据 | ||
待更新、、、、 | ||
|
||
## 🤝 社区参与 | ||
LLM Dojo 是一个不断进化的修炼道场,我们期待你的加入,一起让AI技术更加强大和易用!🪂 | ||
LLM Dojo 期待你的加入!🪂 | ||
|
||
我们非常欢迎你的加入!无论是提出问题(Issue)还是贡献代码(Pull Request),都是对项目的巨大支持。让我们一起构建一个更加完善的开源大模型学习社区! | ||
无论是提出问题(Issue)还是贡献代码(Pull Request),都是对项目的巨大支持。让我们一起构建一个更加完善的开源大模型学习社区! | ||
|
||
## 💌 联系方式 | ||
- GitHub: LLM-Dojo | ||
- Gitter: mst272 | ||
- Email: | ||
- Email: [email protected] | ||
|
||
*** | ||
让我们共同努力,使开源、自由的大模型成为每个学习者学习旅程中不可或缺的一部分! 🌈 | ||
|
||
**愉快学习!** 📘 | ||
*** |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,19 @@ | ||
accelerate==0.21.0 | ||
transformers==4.34 | ||
peft==0.4.0 | ||
bitsandbytes==0.39.0 | ||
loguru==0.7.0 | ||
numpy==1.21.4 | ||
pandas==1.2.5 | ||
tqdm==4.62.3 | ||
deepspeed==0.9.5 | ||
tensorboard | ||
sentencepiece | ||
transformers_stream_generator | ||
tiktoken | ||
einops | ||
httpx | ||
scipy | ||
torch==1.13.1 | ||
flash_attn | ||
datasets |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters