Finetuning Technique

This guides you through picking a fine-tuning technique (SFT, DPO, RLVR, or RLAIF) based on your use case, then validates whether your chosen model actually supports it on SageMaker. It assumes you've already selected a base model and have a use case spec ready. The workflow is straightforward: consults a reference guide to recommend a technique, runs a Python script to check compatibility against the model's available recipes, and either confirms you're good to go or sends you back to pick a different model. Useful safety check before you invest time in a fine-tuning approach that won't work with your model.

GitHub stars: 783
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add awslabs/agent-plugins --skill finetuning-technique --agent claude-code

Installs into .claude/skills of the current project.

Files

Finetuning Technique

Guides the user through selecting a fine-tuning technique based on their use case and validates compatibility with the selected model.

When to Use

User has decided to finetune and needs to choose a technique
User wants to change their finetuning technique
Technique needs to be validated against a selected model

Prerequisites

A base model has been selected (via model-selection skill). The model name and hub must be known.
A use_case_spec.md file exists. If not, activate the use-case-specification skill to generate it first.

Workflow

Step 1: Determine Finetuning Technique

Consult references/finetune_technique_selection_guide.md to recommend the best-fit technique based on the use case and the user's needs (SFT, DPO, RLVR, RLAIF).

Present the recommendation and reasoning to the user. Ask if they'd like to go with the recommendation or prefer a different technique.