Learn: Training and fine-tuning

1. The LLM courseHugging Face · How language models work, from tokens to training.Mark done
2. Learn the basicsPyTorch · Data, models and a training loop, in code.Mark done
3. Model optimizationOpenAI · When to fine-tune, and when a prompt is enough.Mark done
4. PEFTHugging Face · Tuning a big model cheaply with LoRA and friends.Mark done
5. TRLHugging Face · Post-training: supervised tuning, preferences, RL.Mark done

• Pre-training
• Fine-tuning
• LoRA
• RLHF
• Reinforcement learning
• Distillation
• Synthetic data

1. Robust Reinforcement Learning for Dynamic Treatment Regimes under Model and Measurement Uncertainty
2. CAT-alyzing Honesty: Continuous Adversarial Training for Transferable LLM Honesty
3. Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries
4. Topology-Inspired Fine-Tuning for Wind-Field Super-Resolution
5. Training-Free On-Policy Distillation

More in Machine learning →