Update README.md
Browse files
README.md
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
library_name: transformers
|
| 3 |
tags: []
|
| 4 |
---
|
| 5 |
-
# Llama-3-8B-Instruct-abliterated-
|
| 6 |
|
| 7 |
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.
|
| 8 |
|
|
|
|
| 2 |
library_name: transformers
|
| 3 |
tags: []
|
| 4 |
---
|
| 5 |
+
# Llama-3-8B-Instruct-abliterated-v2 Model Card
|
| 6 |
|
| 7 |
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.
|
| 8 |
|