diff --git a/README.md b/README.md index 73e5146..fdf034a 100644 --- a/README.md +++ b/README.md @@ -2,7 +2,7 @@ library_name: transformers tags: [] --- -# Llama-3-8B-Instruct-abliterated-c2 Model Card +# Llama-3-8B-Instruct-abliterated-v2 Model Card This is meta-llama/Llama-3-8B-Instruct with orthogonalized bfloat16 safetensor weights, generated with the methodology that was described in the preview paper/blog post: '[Refusal in LLMs is mediated by a single direction](https://www.alignmentforum.org/posts/jGuXSZgv6qfdhMCuJ/refusal-in-llms-is-mediated-by-a-single-direction)' which I encourage you to read to understand more.