Team of 3 · Deep Learning course · 2026In progress
Transformer with PPO fine-tuning
Building a small language model from scratch and fine-tuning it with proximal policy optimization (PPO).
Stack
- Python
- PyTorch
- Transformers
- PPO
Scope
This is a team course project that is still in progress. A write-up of my part, with results, will follow once the project is complete.