Add support for the Training Method for finetuning, and for Direct-Preference Optimization (DPO)#262

Merged

mryab merged 14 commits intomainfrom

Vprov/dpo_python

Mar 11, 2025

Commits on Feb 28, 2025

Initial DPO update for the finetuning python client
VProv
committed

Commits on Mar 3, 2025

Commits on Mar 4, 2025

Add check that the prompt is the same for the PREFERENCE dataset format
VProv
committed