Update README.md
Browse files
README.md
CHANGED
|
@@ -5,6 +5,7 @@ base_model:
|
|
| 5 |
---
|
| 6 |
|
| 7 |
A jailbroken Meta-Llama-3-8B-Instruct model using weight orthogonalization[1].
|
|
|
|
| 8 |
The model was jailbroken by a combination of JailBreakBench and Alpaca-cleaned datasets, with JailBreakBench samples from HarmfulBench excluded to allow for potential testing.
|
| 9 |
|
| 10 |
[1]: Arditi, Andy, et al. "Refusal in language models is mediated by a single direction." arXiv preprint arXiv:2406.11717 (2024).
|
|
|
|
| 5 |
---
|
| 6 |
|
| 7 |
A jailbroken Meta-Llama-3-8B-Instruct model using weight orthogonalization[1].
|
| 8 |
+
|
| 9 |
The model was jailbroken by a combination of JailBreakBench and Alpaca-cleaned datasets, with JailBreakBench samples from HarmfulBench excluded to allow for potential testing.
|
| 10 |
|
| 11 |
[1]: Arditi, Andy, et al. "Refusal in language models is mediated by a single direction." arXiv preprint arXiv:2406.11717 (2024).
|