Repository navigation

BDPO

Public

forked from huggingface/trl

About

Code of conduct

2 stars

0 watching

Report repository

Name		Name	Last commit message	Last commit date
.github		.github
commands		commands
docker		docker
docs/source		docs/source
examples		examples
scripts		scripts
tests		tests
trl		trl
.gitignore		.gitignore
.pre-commit-config.yaml		.pre-commit-config.yaml
CITATION.cff		CITATION.cff
CODE_OF_CONDUCT.md		CODE_OF_CONDUCT.md
CONTRIBUTING.md		CONTRIBUTING.md
LICENSE		LICENSE
MANIFEST.in		MANIFEST.in
Makefile		Makefile
README.md		README.md
pyproject.toml		pyproject.toml
requirements.txt		requirements.txt
run.sh		run.sh
setup.cfg		setup.cfg
setup.py		setup.py

Repository files navigation

BDPO (Bounded DPO)

This is the repository for Rethinking DPO: The Role of Rejected Responses in Preference Misalignment.

To align a model with BDPO, run a command like:

bash run.sh &

We modified the code based on https://github.com/huggingface/trl.

About

Code of conduct

2 stars

0 watching

Report repository

Releases

Packages

Contributors

Languages