unsloth-dpo
@cuba6112/skillfactory0
0
Direct Preference Optimization (DPO) for aligning models with preference data without separate reward models. Triggers: dpo, preference optimization, rlhf, ref_model=none, patchdpotrainer, dpotrainer.
Install Skill
1Download skill
2Enable skills in Claude
Open claude.ai/settings/capabilities and find the "Skills" section
3Upload to Claude
Click "Upload skill" and select the downloaded ZIP file
Note: Please verify skill by going through its instructions before using it.