This repository contains the code in both PyTorch for our paper.
The config template is in examples/exp. When gamma is set smaller than 1.0, the experiment runs in D^2PO mode.
llamafactory-cli train examples/exp/llama3_full_d2po.yaml-
Notifications
You must be signed in to change notification settings - Fork 0
The official PyTorch implementation of the paper "Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay Perspective".
License
LotuSrc/D2PO
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
The official PyTorch implementation of the paper "Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay Perspective".
Resources
License
Code of conduct
Contributing
Security policy
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published