mcpField
F
finetuning-technique

finetuning-technique

github.com/awslabsDevelopment93269 installsUpdated 3w ago
Repository

About finetuning-technique

A skill for choosing a fine-tuning technique based on a use case and checking whether the selected model supports it. It covers SFT, DPO, RLVR, and RLAIF and confirms the final selections with the user.

Key features

  1. 01Use-case-based technique guidance
  2. 02SFT, DPO, RLVR, and RLAIF selection
  3. 03Model recipe compatibility checks
  4. 04Selection summary

Use cases

  1. 01Choose a technique after deciding to fine-tune
  2. 02Check a technique against a selected base model

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/awslabs/agent-plugins --skill finetuning-technique

After installing, type/finetuning-techniquein Claude Code to confirm it loaded.

Bundled filesreferences/finetune_technique_selection_guide.mdscripts/get_recipes.py

Details

From the project README

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.

Step 2: Validate Technique Availability
  1. Once the user confirms a technique, retrieve the finetuning techniques available for the selected model by running: python finetuning-technique/scripts/get_recipes.py <model-name> <hub-name>
    • This returns only the techniques the model actually supports, filtered to SFT, DPO, RLVR, and RLAIF. Only these four techniques are supported — ignore any other techniques even if the model's recipes include them.
  2. If the chosen technique is available for the model, proceed to Step 3.
  3. If the chosen technique is not available for the model, explain that the selected model does not support it on SageMaker and offer to go back to model-selection to pick a different model that supports the chosen technique.
Step 3: Confirm Selections

Present a summary to the user:

Here's what we've selected:
- Base model: [model name]
- Fine-tuning technique: [SFT/DPO/RLVR/RLAIF]

References

  • references/finetune_technique_selection_guide.md — Technique guidance (SFT/DPO/RLVR/RLAIF)

Comments

Markdown supported