8000 DPO code · Issue #2 · THUDM/LongWriter · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

DPO code #2

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
Open
HaoshengZou opened this issue Aug 14, 2024 · 4 comments
Open

DPO code #2

HaoshengZou opened this issue Aug 14, 2024 · 4 comments

Comments

@HaoshengZou
Copy link

Any plans on releasing the DPO code, or a brief intro of how you conducted long-context DPO?
@bys0318
Copy link
Member
bys0318 commented Aug 15, 2024

Hi! We refer to section 4.2 of our paper for details of DPO. We use the same codebase as ChatGLM-RLHF. We currently do not have plan to release the code and data for DPO.

@HaoshengZou
Copy link
Author

Thanks for the reply!

ChatGLM-RLHF doesn't have code released. Did you modify Megatron-LM for long-context DPO, or use NeMo-Aligner, or other implementation?

@bys0318
Copy link
Member
bys0318 commented Aug 15, 2024

Hi, our DPO code is based on Megatron-LM.

@heyzude
Copy link
heyzude commented Sep 10, 2024

Hi, and thanks for sharing your work!

Could you elaborate more on which specific part of Megatraon-LM (https://github.com/NVIDIA/Megatron-LM) you used?

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

No branches or pull requests
3 participants
@HaoshengZou @heyzude @bys0318
0