Unsloth
Navigate Unsloth install, requirements, notebooks, and fine-tuning vs RAG FAQs to train or adapt open models faster on limited GPU hardware.
Overview
Unsloth is an agent skill most often used in Build (also Validate, Operate) that indexes Unsloth’s fine-tuning and RL documentation so solo builders install, choose models, and run training notebooks efficiently.
Install
npx skills add https://github.com/orchestra-research/ai-research-skills --skill unslothWhat is this skill?
- Documentation index spanning install, update, Docker, Windows, pip, and beginner onboarding paths
- FAQ on whether fine-tuning is right vs misconceptions compared to RAG
- Catalog of Unsloth notebooks and supported model listings for quick starts
- Llms-txt doc bundle indexing 136 pages for agent-friendly retrieval over official docs
- Llms-txt documentation index lists 136 pages under the Unsloth doc bundle
Adoption & trust: 1 installs on skills.sh; 9.4k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You want to fine-tune an open LLM with Unsloth but the docs are spread across install guides, notebooks, and FAQs and you are not sure fine-tuning is even the right move.
Who is it for?
Solo builders with a single GPU who need a guided path through Unsloth install, model choice, and notebook-based fine-tuning or RL experiments.
Skip if: Teams that only consume closed APIs with no local training and no plan to own model weights.
When should I use this skill?
You are installing, updating, or running Unsloth fine-tuning or RL workflows and need the right official doc, requirements check, or notebook entry point.
What do I get? / Deliverables
You land on the correct Unsloth doc section or notebook path for your OS and GPU, with clarity on fine-tuning vs RAG before you start a training job.
- Correct Unsloth install and update procedure for your platform
- Notebook or doc path aligned to your model and training goal
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Fine-tuning with Unsloth is primarily build work, but the bundled beginner and decision docs belong earlier when scoping whether custom weights beat retrieval. Backend subphase covers training pipelines, local GPU setup, Docker/pip installs, and notebook-driven model adaptation.
Where it fits
Read the fine-tuning vs RAG FAQ before committing to custom weights for a narrow domain agent.
Follow pip or Docker install docs then open a catalog notebook to fine-tune your first model on project data.
Use reinforcement-learning oriented Unsloth docs when tuning a tool-calling model for your Claude Code or Cursor agent.
Apply updating and version-pin guidance when a training workstation breaks after a CUDA or Unsloth release change.
How it compares
Skill-backed doc routing for Unsloth workflows, not a managed training cloud or an MCP server that runs jobs for you.
Common Questions / FAQ
Who is unsloth for?
Indie developers and agent builders who want faster open-weight fine-tuning and need structured pointers into Unsloth’s official guides, notebooks, and requirements.
When should I use unsloth?
In validate when deciding fine-tuning versus RAG; in build when installing Unsloth, picking a notebook, or training on custom data; in operate when updating installs or Docker images for ongoing training.
Is unsloth safe to install?
Check the Security Audits panel on this Prism page and verify pip, Docker, or repo sources before granting network and shell access on machines that hold datasets or API keys.
Workflow Chain
Then invoke: knowledge distillation
SKILL.md
READMESKILL.md - Unsloth
# Unsloth Documentation Index ## Categories ### Llms-Txt **File:** `llms-txt.md` **Pages:** 136 # Unsloth Documentation ## Unsloth Documentation - [Unsloth Docs](/get-started/unsloth-docs.md): Train your own model with Unsloth, an open-source framework for LLM fine-tuning and reinforcement learning. - [Beginner? Start here!](/get-started/beginner-start-here.md) - [Unsloth Requirements](/get-started/beginner-start-here/unsloth-requirements.md): Here are Unsloth's requirements including system and GPU VRAM requirements. - [FAQ + Is Fine-tuning Right For Me?](/get-started/beginner-start-here/faq-+-is-fine-tuning-right-for-me.md): If you're stuck on if fine-tuning is right for you, see here! Learn about fine-tuning misconceptions, how it compared to RAG and more: - [Unsloth Notebooks](/get-started/unsloth-notebooks.md): Explore our catalog of Unsloth notebooks: - [All Our Models](/get-started/all-our-models.md) - [Install & Update](/get-started/install-and-update.md): Learn to install Unsloth locally or online. - [Updating](/get-started/install-and-update/updating.md): To update or use an old version of Unsloth, follow the steps below: - [Pip Install](/get-started/install-and-update/pip-install.md): To install Unsloth locally via Pip, follow the steps below: - [Docker](/get-started/install-and-update/docker.md): Install Unsloth using our official Docker container - [Windows Installation](/get-started/install-and-update/windows-installation.md): See how to install Unsloth on Windows with or without WSL. - [AMD](/get-started/install-and-update/amd.md): Fine-tune with Unsloth on AMD GPUs. - [Conda Install](/get-started/install-and-update/conda-install.md): To install Unsloth locally on Conda, follow the steps below: - [Google Colab](/get-started/install-and-update/google-colab.md): To install and run Unsloth on Google Colab, follow the steps below: - [Fine-tuning LLMs Guide](/get-started/fine-tuning-llms-guide.md): Learn all the basics and best practices of fine-tuning. Beginner-friendly. - [What Model Should I Use?](/get-started/fine-tuning-llms-guide/what-model-should-i-use.md) - [Datasets Guide](/get-started/fine-tuning-llms-guide/datasets-guide.md): Learn how to create & prepare a dataset for fine-tuning. - [LoRA Hyperparameters Guide](/get-started/fine-tuning-llms-guide/lora-hyperparameters-guide.md): Optimal lora rank. alpha, number of epochs, batch size & gradient accumulation, QLoRA vs LoRA, target modules and more! - [Tutorial: How to Finetune Llama-3 and Use In Ollama](/get-started/fine-tuning-llms-guide/tutorial-how-to-finetune-llama-3-and-use-in-ollama.md): Beginner's Guide for creating a customized personal assistant (like ChatGPT) to run locally on Ollama - [Reinforcement Learning (RL) Guide](/get-started/reinforcement-learning-rl-guide.md): Learn all about Reinforcement Learning (RL) and how to train your own DeepSeek-R1 reasoning model with Unsloth using GRPO. A complete guide from beginner to advanced. - [Tutorial: Train your own Reasoning model with GRPO](/get-started/reinforcement-learning-rl-guide/tutorial-train-your-own-reasoning-model-with-grpo.md): Beginner's Guide to transforming a model like Llama 3.1 (8B) into a reasoning model by using Unsloth and GRPO. - [Advanced RL Documentation](/get-started/reinforcement-learning-rl-guide/advanced-rl-documentation.md): Advanced documentation settings when using Unsloth with GRPO. - [Memory Efficient RL](/get-started/reinforcement-learning-rl-guide/memory-efficient-rl.md) - [RL Reward Hacking](/get-started/reinforcement-learning-rl-guide/rl-reward-hacking.md): Learn what is Reward Hacking in Reinforcement Learning and how to counter it. - [GSPO Reinforcement Learning](/get-started/reinforcement-learning-rl-guide/gspo-reinforcement-learning.md): Train with GSPO (Group Sequence Policy Optimization) RL in Unsloth. - [Reinforcement Learning - DPO, ORPO & KTO](/get-started/reinforcement-learning-rl-guide/reinforcement-learning-dpo-orpo-and-kto.md): To use the reward mo