Chapter 10 · From Base Model to Assistant
Teach a Preference
Judge candidate summaries and fit a small reward model. Change the rubric and watch the ranking change.
Try it · toy model
12 min
Read the concepts behind it
Chapter 10 · From Base Model to Assistant
Judge candidate summaries and fit a small reward model. Change the rubric and watch the ranking change.
Try it · toy model
Read the concepts behind it