Explore projects

This repository provides a modular framework for language model pretraining followed by reinforcement learning-based fine-tuning using Proximal Policy Optimization (PPO). It supports structured dataset preparation, teacher-based reward modeling, and fine-tuning with trl's PPOTrainer.

Explore Tranings Data from FIT Data Files (e.g. TrainingPeaks, Strava)

Die im Rahmen meiner Bachelorarbeit erstellten Programmierungen

path toward the global warming Eurec4a LES. Planning and Analysis.