cooperleong00's picture
Update README.md
9e5fb70 verified
|
raw
history blame
462 Bytes
metadata
license: llama3
base_model:
  - meta-llama/Meta-Llama-3-8B-Instruct

A jailbroken Meta-Llama-3-8B-Instruct model using weight orthogonalization[1].

The model was jailbroken by a combination of JailBreakBench and Alpaca-cleaned datasets, with JailBreakBench samples from HarmfulBench excluded to allow for potential testing.

[1]: Arditi, Andy, et al. "Refusal in language models is mediated by a single direction." arXiv preprint arXiv:2406.11717 (2024).