Skip to content

provandal/post-training-explorer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

87 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Post-Training Explorer

License: MIT

An interactive educational tool that teaches LLM post-training techniques through a hands-on storage I/O workload classification task. Built for the SNIA DSN Post-Training Webinar.

Live Demo

What You'll Learn

The guided tour walks through a progression of techniques, each building on the last:

  1. Prompt Engineering -- basic prompts, few-shot learning, and their limitations
  2. RAG -- retrieval-augmented generation with vector search
  3. SFT -- supervised fine-tuning with LoRA adapters
  4. DPO -- direct preference optimization
  5. GRPO -- group relative policy optimization (reinforcement learning)

Each stop includes interactive demos, visualizations, and "under the covers" deep dives into how the techniques work.

Project Structure

app/          React frontend (Vite + Tailwind + Zustand + D3)
scripts/      Python training pipeline (SFT, DPO, GRPO)
notebooks/    Jupyter notebooks for Colab

Quick Start

cd app
npm install
npm run dev

The app runs entirely in the browser with precomputed data -- no backend or GPU required.

Training Pipeline

To train your own models, see scripts/README.md for the full pipeline:

  1. Generate synthetic dataset
  2. SFT with LoRA
  3. DPO alignment
  4. GRPO reinforcement learning
  5. Export artifacts
  6. Convert to ONNX for browser inference

All scripts run on a free Colab T4 GPU. See WALKTHROUGH.md for detailed instructions.

Notebooks

Notebook Purpose
Post_Training_Pipeline.ipynb Full SFT, DPO, GRPO pipeline
Traditional_ML_Comparison.ipynb XGBoost/RF baseline comparison
Realistic_LLM_Use_Case.ipynb Unstructured error log classification

Acknowledgments

The four-quadrant optimization framework used throughout this app is adapted from "A Survey of Techniques for Maximizing LLM Performance" by Colin Jarvis and John Allard, presented at OpenAI DevDay (November 2023). Also available in the OpenAI documentation.

License

MIT

About

No description, website, or topics provided.

Resources

License

Stars

0 stars

Watchers

0 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors