unsloth
About
This skill provides expert guidance for fast fine-tuning with Unsloth, offering 2-5x faster training and 50-80% memory reduction. It helps developers implement and debug LoRA/QLoRA optimizations for models like Llama and Mistral. Use it when working with Unsloth's APIs, features, or best practices for efficient model training.
Quick Install
Claude Code
Recommended/plugin add https://github.com/davila7/claude-code-templatesgit clone https://github.com/davila7/claude-code-templates.git ~/.claude/skills/unslothCopy and paste this command in Claude Code to install this skill
Documentation
Unsloth Skill
Comprehensive assistance with unsloth development, generated from official documentation.
When to Use This Skill
This skill should be triggered when:
- Working with unsloth
- Asking about unsloth features or APIs
- Implementing unsloth solutions
- Debugging unsloth code
- Learning unsloth best practices
Quick Reference
Common Patterns
Quick reference patterns will be added as you use the skill.
Reference Files
This skill includes comprehensive documentation in references/:
- llms-txt.md - Llms-Txt documentation
Use view to read specific reference files when detailed information is needed.
Working with This Skill
For Beginners
Start with the getting_started or tutorials reference files for foundational concepts.
For Specific Features
Use the appropriate category reference file (api, guides, etc.) for detailed information.
For Code Examples
The quick reference section above contains common patterns extracted from the official docs.
Resources
references/
Organized documentation extracted from official sources. These files contain:
- Detailed explanations
- Code examples with language annotations
- Links to original documentation
- Table of contents for quick navigation
scripts/
Add helper scripts here for common automation tasks.
assets/
Add templates, boilerplate, or example projects here.
Notes
- This skill was automatically generated from official documentation
- Reference files preserve the structure and examples from source docs
- Code examples include language detection for better syntax highlighting
- Quick reference patterns are extracted from common usage examples in the docs
Updating
To refresh this skill with updated documentation:
- Re-run the scraper with the same configuration
- The skill will be rebuilt with the latest information
GitHub Repository
Related Skills
quantizing-models-bitsandbytes
OtherThis skill quantizes LLMs to 8-bit or 4-bit precision using bitsandbytes, reducing memory usage by 50-75% with minimal accuracy loss for GPU-constrained environments. It supports multiple formats (INT8, NF4, FP4) and enables QLoRA training and 8-bit optimizers. Use it with HuggingFace Transformers when you need to fit larger models into limited memory or accelerate inference.
axolotl
DesignThis skill provides expert guidance for fine-tuning LLMs using the Axolotl framework, helping developers configure YAML files and implement advanced techniques like LoRA/QLoRA and DPO/KTO. Use it when working with Axolotl features, debugging code, or learning best practices for fine-tuning across 100+ models. It offers comprehensive assistance including multimodal support and performance optimization.
hqq-quantization
OtherHQQ enables fast, calibration-free quantization of LLMs down to 2-bit precision without needing a dataset. It's ideal for rapid quantization workflows and for deployment with vLLM or HuggingFace Transformers. Key advantages include significantly faster quantization than methods like GPTQ and support for fine-tuning quantized models.
peft-fine-tuning
OtherThis skill enables parameter-efficient fine-tuning of large language models using LoRA, QLoRA, and other adapter methods, drastically reducing GPU memory requirements. It's ideal for fine-tuning 7B-70B models on consumer hardware by training less than 1% of parameters while maintaining accuracy. The integration with Hugging Face's ecosystem supports multi-adapter serving and rapid iteration with task-specific adapters.