🎯 Overview
unsloth-buddy is a zero-friction LLM fine-tuning skill for Claude Code, Gemini CLI & any ACP agent. Unsloth on NVIDIA · TRL+MPS/MLX on Apple Silicon. Automates env setup, LoRA training (SFT, DPO, GRPO, vision), post-hoc GRPO log diagnostics, evaluation, and export end-to-end. Part of the Gaslamp AI platform.
⚙️ Core Capabilities
- APPLE-SILICON: Provides dedicated abstractions for apple-silicon architectures.
- CLAUDE-CODE: Optimized for claude-code-based execution pipelines.
- DPO: Natively supports dpo integrations out of the box.
- FINE-TUNING: Leverages fine-tuning paradigms for superior performance.
- Production Ready: Extensively tested to prevent edge-case failures.
⚡ Technical Implementation
Building with unsloth-buddy means abstracting away low-level boilerplate. By implementing this utility, you prevent common bottlenecks during runtime execution.
💡 Why Developers Choose unsloth-buddy
It stands out by offering frictionless onboarding and comprehensive tooling for modern development. It is consistently maintained and adapts quickly to new industry standards.