From sagemaker-ai
Selects a fine-tuning technique (SFT, DPO, RLVR, or RLAIF) for the user's use case and validates it against the selected model's available recipes. Requires a base model already selected.
How this skill is triggered — by the user, by Claude, or both
Slash command
/sagemaker-ai:finetuning-techniqueThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Guides the user through selecting a fine-tuning technique based on their use case and validates compatibility with the selected model.
Guides the user through selecting a fine-tuning technique based on their use case and validates compatibility with the selected model.
use_case_spec.md file exists. If not, activate the use-case-specification skill to generate it first.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.
python finetuning-technique/scripts/get_recipes.py <model-name> <hub-name>
Present a summary to the user:
Here's what we've selected:
- Base model: [model name]
- Fine-tuning technique: [SFT/DPO/RLVR/RLAIF]
references/finetune_technique_selection_guide.md — Technique guidance (SFT/DPO/RLVR/RLAIF)npx claudepluginhub awslabs/agent-plugins --plugin sagemaker-aiGenerates code for fine-tuning base models on SageMaker using SFT, DPO, RLVR, and RLAIF trainers. Activates on phrases like 'start training' or 'fine-tune my model'.
Guides LLM fine-tuning with LoRA/QLoRA, dataset preparation, hyperparameter tuning, evaluation, and deployment. Useful for adapting foundation models to custom tasks.
Fine-tune models on Together AI using LoRA, full fine-tuning, DPO, VLM, function-calling, reasoning, and BYOM uploads.