SimPO Training

by Orchestra-Research

SimPO Training is an AI Engineering skill for Claude Code, published by Orchestra-Research in AI-Research-SKILLs.

11.6K stars838 forkson Orchestra-Research/AI-Research-SKILLsAdded 2026/07/19+1% in starsRepository updated 2026/06/16

View source on GitHub Download repo ZIP

aiai-researchclaudeclaude-codeclaude-skillscodexgeminigpt-5grpohuggingfacemachine-leanringmegatronskillsvllm

Install in seconds

Install SimPO Training

Copy SimPO Training into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/main/06-post-training/simpo ~/.claude/skills/simpo

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/Orchestra-Research/AI-Research-SKILLs.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: 06-post-training/simpo/SKILL.md in Orchestra-Research/AI-Research-SKILLs
Installs to: ~/.claude/skills/simpo
Collection: One of 50 skills cataloged from this repository
Category: AI Engineering — 3670 skills

What SimPO Training does

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.

SimPO Training is cataloged under AI Engineering on DirSkills. SimPO Training comes from a repository tagged ai, ai-research, claude, claude-code and claude-skills.

Documentation

README

Excerpt

SimPO - Simple Preference Optimization

Quick start

SimPO is a reference-free preference optimization method that outperforms DPO without needing a reference model.

Installation:

# Create environment
conda create -n simpo python=3.10 && conda activate simpo

# Install PyTorch 2.2.2
# Visit: https://pytorch.org/get-started/locally/

# Install alignment-handbook
git clone https://github.com/huggingface/alignment-handbook.git
cd alignment-handbook
python -m pip install .

# Install Flash Attention 2
python -m pip install flash-attn --no-build-isolation

Training (Mistral 7B):

ACCELERATE_LOG_LEVEL=info accelerate launch \
  --config_file accelerate_configs/deepspeed_zero3.yaml \
  scripts/run_simpo.py \
  training_configs/mistral-7b-base-simpo.yaml

This is the opening of the README. Read the full README on GitHub.

Frequently asked about SimPO Training

What else does Orchestra-Research publish alongside SimPO Training?
SimPO Training is one of 50 skills that DirSkills catalogs from Orchestra-Research/AI-Research-SKILLs, the repository it ships in. Its siblings there include AWQ Quantization, Autoresearch and Axolotl. Each one is a separate skill with its own page in this directory, installs the same way SimPO Training does, and is maintained by Orchestra-Research in that same repository. The rest of the collection is listed on the Orchestra-Research/AI-Research-SKILLs page.
How does SimPO Training compare to other AI Engineering skills?
SimPO Training ranks #363 by stars among the 3670 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of SimPO Training against them. Open each page to compare what they document and how they install.