unsloth
について
このスキルは、Unslothを使用した高速ファインチューニングに関する専門的なガイダンスを提供し、トレーニング速度を2~5倍向上させ、メモリ使用量を50~80%削減します。Unslothソリューションの実装、コードのデバッグ、またはLlamaやMistralなどのモデルにおけるLoRA/QLoRA最適化のベストプラクティスを学ぶ際にご利用ください。
クイックインストール
Claude Code
推奨/plugin add https://github.com/zechenzhangAGI/AI-research-SKILLsgit clone https://github.com/zechenzhangAGI/AI-research-SKILLs.git ~/.claude/skills/unslothこのコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします
ドキュメント
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 リポジトリ
関連スキル
when-optimizing-prompts-use-prompt-architect
その他This skill provides a structured framework for developers to systematically analyze, refine, and optimize prompts for AI systems using evidence-based techniques. It helps eliminate anti-patterns and improve prompt structure, which is triggered by poor response quality or inconsistent outputs. The process includes A/B testing to validate effectiveness and produces an optimized prompt along with an analysis report.
deepspeed
デザインThis skill provides expert guidance for distributed training using Microsoft's DeepSpeed library. It helps developers implement optimization techniques like ZeRO stages, pipeline parallelism, and mixed-precision training. Use this skill when working with DeepSpeed features, debugging code, or learning best practices for large-scale model training.
performance-analysis
その他This skill provides comprehensive performance analysis for Claude Flow swarms, detecting bottlenecks and profiling operations. It generates detailed reports and offers AI-powered optimization recommendations to improve swarm performance. Use it when you need to monitor, analyze, and optimize the efficiency of your Claude Flow implementations.
when-profiling-performance-use-performance-profiler
その他This performance profiling skill helps developers identify and optimize application bottlenecks across CPU, memory, I/O, and network dimensions. It provides comprehensive analysis through baseline measurement, bottleneck detection, and root cause investigation phases. Use this skill when you need systematic performance optimization with tools like perf, Instruments, or clinic.js integration.
