# What is post-training?

Post-training is every training stage that comes after pre-training, including supervised fine-tuning, preference tuning, reinforcement learning and distillation. It is where a model learns how to behave.

## What it covers

[Pre-training](/glossary/pre-training) teaches a model language by having it predict the next token over a large corpus of raw text. Post-training starts from those weights and shapes behavior. Its stages differ in what they learn from:

| Stage | Learns from |
| --- | --- |
| [Supervised fine-tuning](/glossary/supervised-fine-tuning) | examples of the answer you want |
| [Preference tuning](/glossary/preference-tuning) | pairs of a better and a worse answer |
| [Reinforcement fine-tuning](/glossary/reinforcement-fine-tuning) | scores for answers the model generates |
| [Distillation](/glossary/knowledge-distillation) | the output distribution of a teacher model |

Supervised fine-tuning usually comes first. Preference tuning or RL (reinforcement learning) then starts from its checkpoint.

## Post-training vs fine-tuning

The two terms overlap. In everyday use, fine-tuning often means the supervised stage alone. Post-training names the whole set of stages between a pretrained base and the model you ship.

## In Halo

[Halo](/halo) is our open-source framework for post-training. Each method is one name passed to `halo launch`, such as `sft`, `dpo`, `offline-grpo` or `teacher-distill`. All of them read a YAML config, take a Hugging Face checkpoint and a dataset, and write a Hugging Face checkpoint back out. The [training methods](/halo/docs/training-methods) page lists every one.

