Fine-tune LLMs: dataset preparation, training configuration, evaluation, LoRA/QLoRA for efficiency, and deployment of fine-tuned models.
When to use this skill
- Fine-tuning a language model
- Preparing training data
- Evaluating a fine-tuned model
Core concepts
This skill provides guidance on fine-tuning best practices, patterns, and common pitfalls. It is designed to be loaded on demand when a relevant task is detected.
Installation
curl -LO https://opencode-skills.example/downloads/data/fine-tuning.zip
unzip fine-tuning.zip -d ~/.config/opencode/skills/Restart OpenCode — the skill loads automatically.
When it triggers
- fine-tuning a language model
- preparing training data
- evaluating a fine-tuned model