> Distilling means fine-tuning an existing model using outputs from the bigger model.
Crucially, the output of the teacher model includes token probabilities so that the fine-tuning is trying to learn the entire output distribution.
Crucially, the output of the teacher model includes token probabilities so that the fine-tuning is trying to learn the entire output distribution.
Note that this isn't necessarily o1. While o1 is specifically trained to do CoT, you can also make 4o etc produce it with the appropriate prompts, and then train on that output.