# LLM Finetuning

LLM fine-tuning expert for LoRA, QLoRA, dataset preparation, and training optimization

- Repository: https://github.com/RightNow-AI/openfang (18244 stars)
- Category: Data and ML
- License: Apache-2.0
- Last updated: 2026-07-02
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add RightNow-AI/openfang --skill llm-finetuning -g -a claude-code -y`
Codex: `npx skills add RightNow-AI/openfang --skill llm-finetuning -g -a codex -y`
Cursor: `npx skills add RightNow-AI/openfang --skill llm-finetuning -g -a cursor -y`
Gemini CLI: `npx skills add RightNow-AI/openfang --skill llm-finetuning -g -a gemini-cli -y`

## Description

LLM fine-tuning expert for LoRA, QLoRA, dataset preparation, and training optimization

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# LLM Fine-Tuning Expert

A deep learning specialist with hands-on expertise in fine-tuning large language models using parameter-efficient methods, dataset curation, and training optimization. This skill provides guidance for adapting foundation models to specific domains and tasks using LoRA, QLoRA, and the Hugging Face PEFT ecosystem, covering dataset preparation, hyperparameter selection, evaluation strategies, and adapter deployment.

## Key Principles

- Fine-tuning is about teaching a model your task format and domain knowledge, not about teaching it language; start with the strongest base model you can afford to run
- Dataset quality matters far more than quantity; 1,000 carefully curated, diverse, high-quality examples often outperform 100,000 noisy ones
- Use parameter-efficient fine-tuning (LoRA/QLoRA) to reduce memory requirements by orders of magnitude while achieving performance comparable to full fine-tuning
- Evaluate with task-specific metrics and human review, not just perplexity; a model with lower perplexity may still produce worse outputs for your specific use case
- Track every experiment with exact hyperparameters, dataset versions, and base model checkpoints so that results are reproducible and comparable

## Techniques

The rest: https://github.com/RightNow-AI/openfang/blob/HEAD/crates/openfang-skills/bundled/llm-finetuning/SKILL.md