---
id: duyet/codex-claude-plugins/unsloth-training
version: "5651e4c9"
license: none
install: manual
updated: 2026-07-24
---

# Unsloth Training — Unsloth Training accelerates LLM fine-tuning through GRPO (reinforcement learning with reward functions) and SFT (supervised learning with input-output pairs). It cuts VRAM usage by 60% with FP8 training, speeds up mixed-length datasets via automatic packing, and supports vision model tuning, mobile deployment via ExecuTorch, and export to GGUF, Ollama, and vLLM.

Publisher: duyet · Stars: 8 · Updated: 2026-07-24

Install (manual): `git clone https://github.com/duyet/codex-claude-plugins`

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

[View on SkillFed](https://skillfed.io/duyet/codex-claude-plugins/unsloth-training) · [View on GitHub](https://github.com/duyet/codex-claude-plugins)