In this project, we will attempt to recreate GitHub Copilot. Since properly recreating the service requires an immense amount of compute for model training, we will seek to build a Mini Copilot.
This repository contains both educational materials (starter notebooks for basic training) and our actual implementation of recreating GitHub Copilot. Education materials can be found under education/, and our implementation can be found under src/.
Accompanying educational slide decks can be found here (requires UMich login).
Recreating GitHub Copilot involves various parts -- the underlying code completion model, the endpoint serving the model, and the actual application (VSCode extension) using the model.
gpt-2 on a code completion task (code found under src/model).src/backend).registerInlineCompletionItemProvider VSCode API (full implementation found under src/extension). This extension calls our Lambda endpoint to supply the code completion.| Week | Date | Topic |
|---|---|---|
| 1 | 9/22 | Project Overview + Causal Language Modeling (CLM) w/ n-grams |
| 2 | 9/29 | CLM + High Performance Computing (HPC) |
| 3 | 10/6 | CLM Continued + Model Evaluation |
| 4 | 10/20 | Masked Language Modeling (MLM) |
| 5 | 10/27 | Model Deployment |
| 6 | 11/3 | Creating a VSCode Extension |
| 7 | 11/10 | Buffer Week / Going deeper |
| 8 | 11/17 | Final Expo Prep |
Project Members:
Project Leads: