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.

Sign up for GitHub

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

Jump to bottom

Any plan to release the fintune example? #5

Open
SupercarryNg opened this issue Jun 18, 2024 · 3 comments · May be fixed by #44
Open

Any plan to release the fintune example? #5

SupercarryNg opened this issue Jun 18, 2024 · 3 comments · May be fixed by #44

Comments

@SupercarryNg
Copy link

Great Work and Congraduations! Is there any plan to release a fintune example code for DeepSeek-Coder-V2?
I noticed that you mentioned about finetuning this model with 8*A100 GPUs with some skills, could you be more specific? THX!
@guoday
Copy link
Contributor

guoday commented Jun 20, 2024

We use a self-developed fine-tuning framework and code, so we cannot release it. We are currently trying to use the open-source DeepSpeed for fine-tuning. If there is any progress, we will update the README as soon as possible.

@fengyang95
Copy link

We use a self-developed fine-tuning framework and code, so we cannot release it. We are currently trying to use the open-source DeepSpeed for fine-tuning. If there is any progress, we will update the README as soon as possible.

Is there any update on this? Looking forward to your release of the SFT code.

@guoday
Copy link
Contributor

guoday commented Jul 3, 2024

you can refer to the following links:
https://github.com/datawhalechina/self-llm/blob/master/DeepSeek-Coder-V2/04-DeepSeek-Coder-V2-Lite-Instruct%20Lora%20%E5%BE%AE%E8%B0%83.md
https://github.com/DYF-AI/custom-swift

@Muhtasham Muhtasham linked a pull request Aug 25, 2024 that will close this issue
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

add fine-tuning code with lora support Muhtasham/DeepSeek-Coder-V2
3 participants
@fengyang95 @guoday @SupercarryNg