home/categories/llm-ai/davila7-claude-code-templates-cli-tool-components-skills-ai-research-post-training-simpo-skill-md
llm-aidata-ai

simpo-training

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

davila7
maintainer
davila7
آخر تحديث 1/20/2026
النجوم
17577
التفرعات
1576
quick start

Installation and usage

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

التثبيت
$ install --globalskills.sh
الاستخدام

بعد التثبيت، يمكنك استخدام هذه المهارة بتشغيل الأمر التالي في الطرفية:

skills use simpo-training