r1.py script to run R1 with a min-thinking-tokens parameter

from blog Simon Willison's Weblog, | ↗ original
r1.py script to run R1 with a min-thinking-tokens parameter Fantastically creative hack by Theia Vogel. The DeepSeek R1 family of models output their chain of thought inside a ... block. Theia found that you can intercept that closing and replace it with "Wait, but" or "So" or "Hmm" and trick the model into extending its thought process,...