Supervised fine-tuning (SFT)
Further training of a pre-trained model on example prompts paired with the replies people want.
Qwen’s technical report says that post-training began with over a million supervised fine-tuning examples, followed by two preference-based stages: training on about 150,000 preference pairs, then an online method called GRPO.
See it in action
Try supervised fine-tuning (sft) hands-on in the lesson Instruction tuning and RLHF, part of the How AI assistants work course.