Concept record · edition 1.0.0

Post-training

What the term means here

Adaptation after pre-training — supervised fine-tuning, preference optimization, reinforcement learning from human or model feedback.

Why it matters

Most of the difference between a raw pre-trained model and a deployed assistant is here, which means capability comparisons across models often compare post-training pipelines.

Related claim records · 2

Sources used here · 1

primary paperContent verified

Training language models to follow instructions with human feedback

Ouyang et al. · 2022

The post-training method that separated instruction-following from raw pre-training.

Source record →

Related concepts