Mastery card
I can explain Instruction Tuning
Training a model to follow human instructions helpfully.
Instruction tuning fine-tunes a base model on instruction-response pairs so it better follows user requests in chat form.
Sticky trick
Base models complete text; instruction-tuned models take orders.
Take into the room
In plain English, what is Instruction Tuning?
Or open the share card 📝
Or start your own 5-word trail from home.