---
id: ScientiaCapital/skills/unsloth-training-skill
version: "1a2340c5"
license: none
install: manual
updated: 2026-07-06
---

# Unsloth Training Skill — This skill teaches efficient LLM fine-tuning via Unsloth, covering GRPO (reinforcement learning with reward functions) and SFT (supervised training). Learn FP8 training for 60% VRAM reduction, automatic packing for 2–5x speedup, vision model tuning, mobile deployment via QAT, Docker containerization, and export to GGUF and other formats.

Publisher: ScientiaCapital · Stars: 26 · Updated: 2026-07-06

Install (manual): `git clone https://github.com/ScientiaCapital/skills`

*Unlicensed repository - metadata only, no file contents reproduced.*

[View on SkillFed](https://skillfed.io/ScientiaCapital/skills/unsloth-training-skill) · [View on GitHub](https://github.com/ScientiaCapital/skills)