Skill UI

Provides expert guidance on Unsloth to accelerate fine-tuning via LoRA/QLoRA, reduce memory usage, and streamline API usage, debugging, and best practices.

A comprehensive skill for fine-tuning and training large language and vision models using advanced techniques like TRL (SFT, DPO, GRPO) or Unsloth. This process runs entirely on managed Hugging Face cloud GPUs, eliminating the need for local GPU setup. It supports modern training workflows, model conversion (GGUF for local deployment), and ensures seamless artifact storage to the Hugging Face Hub.

Train or fine-tune language and vision models using TRL or Unsloth on Hugging Face Jobs infrastructure. Supports SFT, DPO, GRPO methods and GGUF conversion for local deployment. Requires Pro account and HF_TOKEN for Hub saving. Optimized for cloud GPU training without local setup.

Fine-tune LLMs on a single consumer GPU with Unsloth Core. Covers VRAM sizing, LoRA/QLoRA, GRPO/DPO post-training, chat-template correctness, and GGUF export.