DPO/ORPO example notebooks#3893

Draft

igorts-git wants to merge 3 commits into

mainfrom

igorts/dpo-examples-notebooks

Commits on May 15, 2026

Feature: add DPO and ORPO preference data preprocessing pipeline utilities
igorts-git
committed
Feature: integrate post-training Direct Preference Optimization (DPO) trainer and execution utilities
igorts-git
committed
Feature: integrate standalone DPO and ORPO demonstration notebook with dynamic algorithm toggle and CI validation
igorts-git
committed