npx machina-cli add skill Orchestra-Research/AI-Research-SKILLs/unsloth --openclawUnsloth 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
Source
git clone https://github.com/Orchestra-Research/AI-Research-SKILLs/blob/main/03-fine-tuning/unsloth/SKILL.mdView on GitHub Overview
Unsloth provides expert guidance for fast fine-tuning, delivering 2-5x faster training and 50-80% memory savings through LoRA/QLoRA optimizations. It guides you from beginner concepts to feature-specific APIs, supported by official references and code patterns. This skill helps you implement efficient fine-tuning workflows and leverage optimization techniques effectively.
How This Skill Works
The skill aggregates official Unsloth documentation into a structured workflow: start with beginner tutorials, then consult feature-specific references (API, guides), and finally apply code patterns from the quick reference sections. It points you to the references directory for detailed explanations and concrete examples to accelerate development.
When to Use It
- Working with unsloth
- Asking about unsloth features or APIs
- Implementing unsloth solutions
- Debugging unsloth code
- Learning unsloth best practices
Quick Start
- Step 1: Start with the getting_started or tutorials reference files for foundational concepts
- Step 2: Use the appropriate category reference file (api, guides, etc.) for detailed information on specific features
- Step 3: Review the quick reference patterns and apply them to your fine-tuning workflow
Best Practices
- Follow official documentation and references (e.g., llms-txt.md, API guides) for accurate guidance
- Begin with the getting_started or tutorials references to grasp fundamentals
- Use the appropriate category references (api, guides, etc.) for detailed feature information
- Consult the quick reference patterns for common usage scenarios
- Validate implementations against code examples and language annotations in references
Example Use Cases
- Debugging a LoRA-based fine-tuning loop to reduce memory usage
- Fine-tuning a model (e.g., Llama/Mistral) with Unsloth using QLoRA to save memory
- Exploring unsloth APIs to implement a custom training script
- Applying the quick reference patterns to bootstrap a pilot fine-tuning workflow
- Referencing references/llms-txt.md for model documentation during setup
Frequently Asked Questions
Related Skills
quantizing-models-bitsandbytes
Orchestra-Research/AI-Research-SKILLs
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
axolotl
Orchestra-Research/AI-Research-SKILLs
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
deepspeed
Orchestra-Research/AI-Research-SKILLs
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention
awq-quantization
Orchestra-Research/AI-Research-SKILLs
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.
optimizing-attention-flash
Orchestra-Research/AI-Research-SKILLs
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
gptq
Orchestra-Research/AI-Research-SKILLs
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
