💬Instruction Tuning
Also known as Supervised Fine-Tuning, SFT
More training on asks paired with good answers. Then the model does what you ask.
Think of it like
Think of it like you show a helper lots of notes. Each one has the right reply under it.
Example
A team writes 50,000 pairs such as 'List three uses for salt' with a good list under it. After training on them, their base model starts to answer like a helper.
Why it matters
It is the step that makes a model useful to talk to. Without it, you get a text guesser, not a helper.
Definition
Common mistake
Key takeaways
- 1Request and reply pairs. Many kinds of task.
- 2Turns base into helper. It learns to follow.
- 3Quality over count. Good pairs matter most.