simpo-training
๐ฏSkillfrom zechenzhangagi/ai-research-skills
|Performs Simple Preference Optimization (SIMPO) training for fine-tuning language models using a lightweight preference learning approach.
Part of
zechenzhangagi/ai-research-skills(83 items)
Installation
npx @orchestra-research/ai-research-skillsnpx @orchestra-research/ai-research-skills list # View installed skillsnpx @orchestra-research/ai-research-skills update # Update installed skills/plugin marketplace add orchestra-research/AI-research-SKILLs/plugin install fine-tuning@ai-research-skills # Axolotl, LLaMA-Factory, PEFT, Unsloth+ 4 more commands
Skill Details
Overview
# AI Research Engineering Skills Library
> The most comprehensive open-source library of AI research engineering skills for AI agents
**82 Skills Powering AI Research in 2026**
| | | | |:---:|:---:|:---:| | Model Architecture (5) | Fine-Tuning (4) | Post-Training (8) | | Distributed Training (6) | Optimization (6) | Inference (4) | | Tokenization (2) | Data Processing (2) | Evaluation (3) | | Safety & Alignment (3) | Agents (4) | RAG (5) | | Multimodal (7) | Prompt Engineering (4) | MLOps (3) | | Observability (2) | Infrastructure (3) | Mech Interp (4) | | Emerging Techniques (6) | ML Paper Writing (1) | |
---
Table of Contents
- [Our Mission](#our-mission)
- [Path Towards AI Research Agent](#path-towards-ai-research-agent)
- [Available AI Research Engineering Skills](#available-ai-research-engineering-skills)
- [Demos](#demos)
- [Skill Structure](#skill-structure)
- [Roadmap](#roadmap)
- [Repository Structure](#repository-structure)
- [Use Cases](#use-cases)
- [Contributing](#contributing)
- [Community](#community)
Our Mission
We provide the layer of Engineering Ability that enable your coding agent to write and conduct AI research experiments, including preparing datasets, executing training pipelines, deploying models, and building your AI agents.
System diagram of an AI research agent
Path Towards AI Research Agent
Modern AI research requires mastering dozens of specialized tools and frameworks.
AI Researchers spend more time debugging infrastructure than testing hypothesesโslowing the pace of scientific discovery.
We provide a comprehensive library of expert-level research engineering skills that enable AI agents to autonomously implement and execute different stages of AI research experimentsโfrom data preparation and model training to evaluation and deployment.
- Specialized Expertise - Each skill provides deep, production-ready knowledge of a specific framework (Megatron-LM, vLLM, TRL, etc.)
- End-to-End Coverage - 82 skills spanning model architecture, tokenization, fine-tuning, mechanistic interpretability, data processing, post-training, distributed training, optimization, evaluation, inference, infrastructure, agents, RAG, multimodal, prompt engineering, MLOps, observability, emerging techniques, and ML paper writing
- Research-Grade Quality - Documentation sourced from official repos, real GitHub issues, and battle-tested production workflows
Available AI Research Engineering Skills
Quality over quantity: Each skill provides comprehensive, expert-level guidance with real code examples, troubleshooting guides, and production-ready workflows.
๐ฆ Quick Install (Recommended)
Install skills to any coding agent (Claude Code, OpenCode, Cursor, Codex, Gemini CLI, Qwen Code) with one command:
```bash
npx @orchestra-research/ai-research-skills
```
This launches an interactive installer that:
- Auto-detects your installed coding agents
- Installs skills to
~/.orchestra/skills/with symlinks to each agent - Offers everything, quickstart bundle, by category, or individual skills
- Updates installed skills with latest versions
- Uninstalls all or selected skills
```bash
# Interactive installer (recommended)
npx @orchestra-research/ai-research-skills
# Direct commands
npx @orchestra-research/ai-research-skills list # View installed skills
npx @orchestra-research/ai-research-skills update # Update installed skills
```
Install skill categories directly using the Claude Code CLI:
```bash
# Add the marketplace
/plugin marketplace add orchestra-research/AI-research-SKILLs
# Install by category (20 categories available)
/plugin install fine-tuning@ai-research-skills # Axolotl, LLaMA-Factory, PEFT, Unsloth
/plugin install post-training@ai-research-skills # TRL, GRPO, OpenRLHF, SimPO, verl, slime, miles, torchforge
/plugin install inference-serving@ai-research-skills # vLLM, TensorRT-LLM, llama.cpp, SGLang
/plugin install distributed-training@ai-research-skills
/plugin install optimization@ai-research-skills
```
All 20 Categories (82 Skills)
| Category | Skills | Included |
|----------|--------|----------|
| Model Architecture | 5 | LitGPT, Mamba, NanoGPT, RWKV, TorchTitan |
| Tokenization | 2 | HuggingFace Tokenizers, SentencePiece |
| Fine-Tuning | 4 | Axolotl, LLaMA-Factory, PEFT, Unsloth |
| Mech Interp | 4 | TransformerLens, SAELens, pyvene, nnsight |
| Data Processing | 2 | NeMo Curator, Ray Data |
| Post-Training | 8 | TRL, GRPO, OpenRLHF, SimPO, verl, slime, miles, torchforge |
| Safety | 3 | Constitutional AI, LlamaGuard, NeMo Guardrails |
| Distributed | 6 | DeepSpeed, FSDP, Accelerate, Megatron-Core, Lightning, Ray Train |
| Infrastructure | 3 | Modal, Lambda Labs, SkyPilot |
| Optimization | 6 | Flash Attention, bitsandbytes, GPTQ, AWQ, HQQ, GGUF |
| Evaluation | 3 | lm-eval-harness, BigCode, NeMo Evaluator |
| Inference | 4 | vLLM, TensorRT-LLM, llama.cpp, SGLang |
| MLOps | 3 | W&B, MLflow, TensorBoard |
| Agents | 4 | LangChain, LlamaIndex, CrewAI, AutoGPT |
| RAG | 5 | Chroma, FAISS, Pinecone, Qdrant, Sentence Transformers |
| Prompt Eng | 4 | DSPy, Instructor, Guidance, Outlines |
| Observability | 2 | LangSmith, Phoenix |
| Multimodal | 7 | CLIP, Whisper, LLaVA, BLIP-2, SAM, Stable Diffusion, AudioCraft |
| Emerging | 6 | MoE, Model Merging, Long Context, Speculative Decoding, Distillation, Pruning |
| ML Paper Writing | 1 | ML Paper Writing (LaTeX templates, citation verification) |
๐๏ธ Model Architecture (5 skills)
- [LitGPT](01-model-architecture/litgpt/) - Lightning AI's 20+ clean LLM implementations with production training recipes (462 lines + 4 refs)
- [Mamba](01-model-architecture/mamba/) - State-space models with O(n) complexity, 5ร faster than Transformers (253 lines + 3 refs)
- [RWKV](01-model-architecture/rwkv/) - RNN+Transformer hybrid, infinite context, Linux Foundation project (253 lines + 3 refs)
- [NanoGPT](01-model-architecture/nanogpt/) - Educational GPT in ~300 lines by Karpathy (283 lines + 3 refs)
- [TorchTitan](01-model-architecture/torchtitan/) - PyTorch-native distributed training for Llama 3.1 with 4D parallelism
๐ค Tokenization (2 skills)
- [HuggingFace Tokenizers](02-tokenization/huggingface-tokenizers/) - Rust-based, <20s/GB, BPE/WordPiece/Unigram algorithms (486 lines + 4 refs)
- **[
More from this repository10
ml-paper-writing skill from zechenzhangagi/ai-research-skills
Performs efficient semantic vector search and similarity matching using Qdrant's vector database for AI-powered information retrieval and recommendation systems.
Orchestrates seamless multi-cloud deployment and management of AI workloads across different cloud providers using SkyPilot's infrastructure automation capabilities.
Enables AI agents to leverage LangChain's framework for building complex language model workflows and chaining together different AI components and tools.
Orchestrates multi-agent collaboration using CrewAI for complex research tasks, enabling specialized AI agents to work together systematically.
Generates and manages autonomous AI agents using AutoGPT's framework for executing complex, multi-step research and problem-solving tasks.
Generates and manages fine-tuning configurations and workflows for Llama language models, streamlining the process of customizing and training large language models.
Enables distributed and efficient machine learning training across multiple GPUs or machines using Hugging Face's Accelerate library.
Logs and tracks machine learning experiments, model performance, and hyperparameters using Weights & Biases platform for comprehensive AI research visualization.
Enables fine-tuning large language models using the Transformers Reinforcement Learning (TRL) library for efficient and customizable model adaptation.