Finetuning
Automates the full serverless fine-tuning workflow on SageMaker, from code generation to job monitoring. Supports SFT, DPO, RLVR, and RLAIF techniques with proper scaffolding for each. The workflow is thorough, maybe overly so: it checks prerequisites like use case specs and model selection, handles EULA acceptance for Meta models, and even helps you build custom RLVR reward functions if needed. Code generation follows strict templates with exact imports and minimal improvisation. Worth noting that it adapts output based on model family (strips EULA code for non-Meta, removes certain hyperparameters for Nova). If you're doing one-off experiments this might feel heavy, but for repeatable training pipelines it keeps you from missing steps.
- skills.sh installs
- 154
- GitHub stars
- 938
- last updated
- Jun 11, 2026
Install
$ npx -y skills add awslabs/agent-plugins --skill finetuning --agent claude-codeInstalls into .claude/skills of the current project.
Files
Prerequisites
Before starting this workflow, verify:
-
A
use_case_spec.mdfile exists- If missing: Activate the
use-case-specificationskill first, then resume - DON'T EVER offer to create a use case spec without activating the use-case-specification skill.
- If missing: Activate the
-
A fine-tuning technique (SFT, DPO, RLVR, RLAIF, or CPT/RFT (for Nova)) and base model have already been selected
- If missing: Activate the
model-selectionand/orfinetuning-techniqueskills to collect what's missing, then resume - Don't make recommendations on the spot. You MUST activate the appropriate skill.
- If missing: Activate the
-
A base model name available on SageMakerHub has been identified
- If missing: Activate the
model-selectionskill to get it - Important: Only use the model name that
model-selectionretrieves, as it may differ from other commonly used names for the same model
- If missing: Activate the
-
The SDK environment has been verified (SDK version, region, execution role)
- If not done: Activate the
sdk-getting-startedskill first, then resume
- If not done: Activate the
-
A training dataset uploaded to a bucket in the environment's default region.
- If not met: Help the user upload the dataset to the correct S3
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/awslabs/agent-plugins
- Categories
- Backend & APIs, AI & Agent Building, Productivity & Planning, Cloud & Infrastructure
- License
- Apache-2.0
- First seen
- Jun 11, 2026
More from awslabs/agent-plugins
All 32- Model Deployment154
- Dataset Transformation153
- Hyperpod Ssm150
- Hyperpod Version Checker149
- Hyperpod Issue Report147
- Model Evaluation140
- Amplify Workflow101
- Amazon Location Service
- Api Gateway
- Aws Lambda Durable Functions
- Aws Lambda Managed Instances
- Aws Transform
- Document Service
- Dsql
- Elastic Beanstalk
- Finetuning Technique
- Hyperpod Cluster Debugger
- Hyperpod Nccl
- Hyperpod Node Debugger
- Hyperpod Performance Debugger
- Hyperpod Slurm Debugger
- Model Selection
- Sdk Getting Started
- Aws Architecture Diagram358
Recommended
More Backend & APIs
model-deploymentawslabs/agent-pluginsGenerates code that deploys fine-tuned models from SageMaker Serverless Model Customization to SageMaker endpoints or Bedrock. Use when the user says "deploy my154skills.sh installs
axiom-spritekit-refcharleswiltgen/axiomSpriteKit API reference — all node types, physics body creation, action catalog, texture atlases, constraints, scene setup, particles, SKRenderer154skills.sh installs
wiki-research-looprohitg00/pro-workflowAuto-grow a pro-workflow wiki by running a budget-capped BFS research loop over pluggable source fetchers (web, arXiv, GitHub). Each iteration pops a seed from 154skills.sh installswiki-viewerrohitg00/pro-workflowRender a self-contained HTML viewer for a pro-workflow wiki. Pages, sources, claims, seed queue, page-link graph and full-text search all in one file. No extern153skills.sh installs
good-writing-zhyelban/orz99-skills中文好寫作指南：提升中文寫作品質與改寫既有文章。基於 Paul Graham、余光中、王鼎鈞的寫作智慧。 使用時機： - 用戶說「潤稿」「改寫」「rewrite」「讓文字更順」 - 用戶要求「改善文筆」「寫好一點」「高品質中文」 - 用戶提供文章並要求修改或潤飾 - 需要產出高品質中文內容時 技術文件（README、A153skills.sh installs
doca-programming-guideNVIDIA/skillsUse this skill when the user is writing their first DOCA app or asking a library-agnostic programming question — picking a shipped sample to copy and modify, wi151skills.sh installs