Generate Unsloth training notebooks and scripts. Use when the user wants to create a training notebook, configure fine-tuning parameters, or set up SFT/DPO/GRPO training.
/plugin marketplace add chrisvoncsefalvay/funsloth/plugin install funsloth@funslothThis skill inherits all available tools. When active, it can use any tool Claude has access to.
notebooks/sft_template.ipynbreferences/HARDWARE_GUIDE.mdreferences/MODEL_SELECTION.mdreferences/TRAINING_METHODS.mdscripts/train_dpo.pyscripts/train_grpo.pyscripts/train_sft.pyGenerate training notebooks for fine-tuning with Unsloth.
Copy and customize the template notebook:
notebooks/sft_template.ipynb
Or use a training script directly:
python scripts/train_sft.py # Supervised fine-tuning
python scripts/train_dpo.py # Direct preference optimization
python scripts/train_grpo.py # Group relative policy optimization
Ask the user which mode they prefer:
Use these production-ready defaults:
| Parameter | Default | Reasoning |
|---|---|---|
| Model | unsloth/llama-3.1-8b-unsloth-bnb-4bit | Good balance |
| Max seq length | 2048 | Covers most use cases |
| Load in 4-bit | True | 70% VRAM reduction |
| LoRA rank | 16 | Good trade-off |
| Batch size | 2 | Works on 8GB+ VRAM |
| Gradient accumulation | 4 | Effective batch of 8 |
| Learning rate | 2e-4 | Unsloth recommended |
| Epochs | 1 | Often sufficient |
Ask questions in order. See MODEL_SELECTION.md for model options and TRAINING_METHODS.md for technique details.
Generate a notebook with interactive configuration widgets. Users select options at runtime.
Generate notebooks with these sections:
Ask where to run training:
funsloth-hfjobs)funsloth-runpod)funsloth-local)notebook_path: "./training_notebook.ipynb"
model_name: "unsloth/llama-3.1-8b-unsloth-bnb-4bit"
dataset_name: "mlabonne/FineTome-100k"
technique: "SFT"
lora_rank: 16
max_seq_length: 2048
batch_size: 2
learning_rate: 2e-4
num_epochs: 1
Use when working with Payload CMS projects (payload.config.ts, collections, fields, hooks, access control, Payload API). Use when debugging validation errors, security issues, relationship queries, transactions, or hook behavior.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.