Post-training
What changes a pretrained model into a useful and safe assistant.
- Supervised fine-tuning
- Instruction tuning
- Reward modelling
- RLHF
- Preference optimization
- AI feedback and constitutional methods
- Parameter-efficient fine-tuning
- Model merging
- Safety training and refusals
- System prompts and personas
- Continued pretraining and domain adaptation
This area has no pages yet. The coverage plan lists the pages that it needs. You can write one of them. Read how to contribute.