Skip to content

Instantly share code, notes, and snippets.

@ruvnet

ruvnet/Reasoning.ipynb

Created March 9, 2024 14:08
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save ruvnet/1d03bba3ebb00a16e3931125a78a755c to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save ruvnet/1d03bba3ebb00a16e3931125a78a755c to your computer and use it in GitHub Desktop.
Download ZIP
Self reasoning framework
Display the source blob
Display the rendered blob
Raw
Reasoning.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@BradKML
Copy link

BradKML commented Aug 21, 2025

Considering how methods like "Pass@K" training and "Dr. GRPO" are de-biasing LLM thinking, I wonder if these methods also work with prompt engineering. The art of this would be to know which method to use for which specific task types. https://github.com/RUCAIBox/Passk_Training https://github.com/sail-sg/understand-r1-zero

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment