Skip to content

Add sample packing for DPO, PPO #2177

Open
@SalmanMohammadi

Description

@SalmanMohammadi
No description provided.

Metadata

Metadata

Labels

enhancementNew feature or requestrlhfAnything related to reinforcement learning w/ human feedback

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions