Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Chinese-Vicuna-lora-7b-3epoch-belle-and-guanaco这个模型是怎么训练出来的 #87

Closed
hyb1234hi opened this issue Apr 18, 2023 · 6 comments

Comments

@hyb1234hi
Copy link

hyb1234hi commented Apr 18, 2023

本人第一次接触这类项目,请问文档里的Chinese-Vicuna-lora-7b-3epoch-belle-and-guanaco这个模型是怎么训练出来的,finetune.py的输出又是什么,checkpoint-final是什么,和13B-based lora model什么关系。另外CPU推理的tools/merge_lora_for_cpp.py这个文件也没有。可以从huggingface上加载我们的模型或其他lora模型,为什么文件名是generate.py,需要generate生成什么呢?断点重训/增量训练支不支持单卡写法呢?哪些是你们自己训练的或是三方的,哪些是我们需要我们自己可以训练的呢?

@Facico
Copy link
Owner

Facico commented Apr 18, 2023

1、用我们的finetune脚本,把DATA_PATH设置成下载后的merge.json跑出来的
2、finetune.py输出模型
3、checkpoint-final就是Chinese-Vicuna-lora-7b-3epoch-belle-and-guanaco,和13B-based lora model没有关系
4、merge_lora_for_cpp.py名字改为merge_lora.py了,这个我等下去改文档
5、generate就是推理用的,根据输入生成输出
6、支持
7、那些lora模型都是我们训练的,lora模型是我们可以训练的

@hyb1234hi
Copy link
Author

感谢回答
3.13B-based lora model我们这边也可以训练出来么。
5. generate的输入model_path是https://huggingface.co/decapoda-research/llama-7b-hf么,那么lora_path对应的是Chinese-Vicuna-lora-7b-3epoch-belle-and-guanaco么,还是lora_path只是个输出路径。
6. 断点重训/增量训练单卡写法是什么。
7. 我们可以训练哪些呢。

@Facico
Copy link
Owner

Facico commented Apr 19, 2023

3、都可以,7b,13b,30b等把基底模型改一下都能训
5、model_path是基底模型,可以仔细阅读我们的readme和相关的脚本
6、和finetune.sh的单卡写法一致
7、你的问题有点抽象

@hyb1234hi
Copy link
Author

hyb1234hi commented Apr 19, 2023

也就是你们的代码是
1.参考https://github.com/tloen/alpaca-lora。
2.使用decapoda-research/llama-7b-hf,merge.json作为输入,然后利用finetune.py脚本,训练出类似Chinese-Vicuna-lora-7b-3epoch-belle-and-guanaco的模型。
3.最后用类似Chinese-Vicuna-lora-7b-3epoch-belle-and-guanaco的模型和decapoda-research/llama-7b-hf作为输入,然后用对话脚本使用gradio生成一个网页(用于指令问答)的项目呗。

@Facico
Copy link
Owner

Facico commented Apr 19, 2023

最基础的流程可以这么理解

@hyb1234hi
Copy link
Author

感谢回答

@Facico Facico closed this as completed Apr 24, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants