Pinned Loading

1. latentqa latentqa Public

   Python 31 13

2. machiavelli machiavelli Public

   Python 150 36

3. centerforaisafety/wmdp centerforaisafety/wmdp Public

   WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning method which reduces LLM performance on WMDP while retaining …

   Jupyter Notebook 166 43