Popular repositories Loading

1. arbiter arbiter Public

   Run HuggingFace models through freeform questions and judge responses with an LLM.

   Python 4 1

2. psychological-safety psychological-safety Public

   Python 2

3. diffing-toolkit diffing-toolkit Public

   Forked from science-of-finetuning/diffing-toolkit

   A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.

   Python 1 1

4. aisilab.github.io aisilab.github.io Public

   Website of the AI Safety & Interpretability Lab at SDU

   HTML 1

5. Superadditive-cooperation-LLMs Superadditive-cooperation-LLMs Public

   Forked from pippot/Superadditive-cooperation-LLMs

   Study on super additive cooperation between Large Language Model agents in an Iterated Prisoner's Dilemma tournament

   Python

6. Prolog-as-a-Tool Prolog-as-a-Tool Public

   Forked from niklasmellgren/grpo-prolog-inference

   Reinforcement fine-tuning LLMs with GRPO to generate Prolog code for symbolic reasoning and inference

   Python