Chrisvoncsefalvay Funsloth
- 5 repo stars
- Updated December 18, 2025
- chrisvoncsefalvay/funsloth
chrisvoncsefalvay-funsloth is a Claude Code plugin that guides Unsloth-based LLM fine-tuning, dataset handling, validation, and deployment-oriented model workflows.
About
chrisvoncsefalvay-funsloth is a Claude Code plugin aimed at developers who are customizing language models with Unsloth instead of hand-rolling every training script. It packages a complete fine-tuning management flow: preparing and validating datasets, running LoRA or QLoRA training, and moving toward deployment artifacts you can host on Hugging Face. Use it when you already know you need a tuned model for a product feature, support bot, or vertical agent, and you want the agent to follow a consistent checklist rather than improvising notebook cells. The repo is small and focused—one plugin keyword cluster around training, validation, and workflow—so it complements generic coding skills rather than replacing MLOps platforms. It matters because fine-tuning mistakes (leaky data, wrong adapter settings, skipped validation) are expensive on GPU time; a guided plugin reduces rework for developers who are not full-time ML engineers.
- End-to-end Unsloth fine-tuning workflow (dataset → train → validate)
- LoRA and QLoRA training paths for efficient GPU use
- Dataset generation, validation, and management steps in one bundle
- Hugging Face–oriented model deployment and export guidance
- Notebook-friendly workflow for iterative training runs
Chrisvoncsefalvay Funsloth by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
/plugin install chrisvoncsefalvay-funsloth@chrisvoncsefalvay/funslothAdd your badge
Show developers this plugin is listed on Skillselion. Paste this into your README.
| repo stars | ★ 5 |
|---|---|
| Last updated | December 18, 2025 |
| Repository | chrisvoncsefalvay/funsloth ↗ |
What it does
Install this when you want a single Claude Code plugin to steer Unsloth fine-tuning from dataset prep through validation and Hugging Face–ready model output.
Who is it for?
Best when you're fine-tuning open models with Unsloth/LoRA and want agent-driven checklists inside Claude Code.
Skip if: Skip if you only need inference APIs with no custom training, or orgs running managed fine-tuning entirely outside the repo.
What you get
After you add the plugin, Claude Code can follow a structured Unsloth workflow from dataset prep through training and validation toward a deployable Hugging Face model.
- Validated dataset and training configuration aligned to Unsloth
- Trained LoRA or QLoRA adapter checkpoints
- Deployment-oriented export steps toward Hugging Face hosting
By the numbers
- 1 plugin in the chrisvoncsefalvay/funsloth bundle
- Repository slug: chrisvoncsefalvay-funsloth
- Keyword set covers dataset, fine-tuning, LoRA, QLoRA, validation, deployment, and workflow
Recommended Plugins
Abix5 Memory HindsightHindsight memory bank integration for Claude Code
Agentic Dev Io Mcp Code ExecutionToken-efficient MCP server interaction through code execution.1
Agneym Agneym Claude MarketplaceClaude Code plugin marketplace for Agney's plugins
Akkomar Mozdata Claude Plugin1 plugin
Amitpatole Claude Genkit PluginFirebase Genkit Plugin for Claude Code12
Aserper RtfdSpoonfeed your AI coding assistant with up to date documentation efficiently and without using a cloud service with the RTFD mcp server that runs on YOUR machine without any API key requirements!14How it compares
LLM training workflow plugin, not a general coding skill or MCP data connector.
FAQ
Who is Chrisvoncsefalvay Funsloth for?
It is for and small-team developers who customize LLMs with Unsloth and want Claude Code to manage datasets, training, and validation in one repeatable flow.
When should I use Chrisvoncsefalvay Funsloth?
Use it during Build when you are implementing a tuned model—after you have scoped the use case and before you wire the adapter into production inference.
How do I add Chrisvoncsefalvay Funsloth to my agent?
Install or register the plugin from the chrisvoncsefalvay/funsloth repository in your Claude Code plugins setup, then invoke it when starting a fine-tuning or dataset task.