EulerForge Tutorials
All Tutorials
- Getting Started
- 0. Data Preprocessing
- 1. Dense LoRA
- 2. Mixture-of-LoRAs
- 3. MoE Expert LoRA (Dense → MoE)
- 4. Native MoE Expert LoRA (Mixtral)
- 5. DPO Training
- 6. ORPO Training
- 7. Reward Model (RM) Training
- 8. PPO (RLHF) Training
- 9. MoE Stability & Validation
- 10. Metrics Monitoring
- 11. Inference Benchmark
- 12. Hyperparameter Search (Grid / Random / Bayes)
- 13. LLaMA Fine-Tuning
- 14. LoRA Handoff Scheduling
- 15. Loading Models
- 16. HuggingFace Export
- 17. Scratch Pretraining
- 18. Training Pipeline (SFT → PPO)
- 19. Data Collection for Labs
- 20. Lab: Math / Coding Model
- 21. Lab: Chain-of-Thought Reasoning Model
- 22. Lab: Korean Finance Copilot
- 23. Lab: Full MoE Pipeline (SFT → DPO → RM → PPO)
GitHub Repository: https://github.com/eulerwa/eulerforge