Update README.md
Browse files
README.md
CHANGED
|
@@ -12,7 +12,7 @@ library_name: transformers
|
|
| 12 |
|
| 13 |
# internlm2_5-7b-chat-abliterated
|
| 14 |
|
| 15 |
-
|
| 16 |
|
| 17 |
Check out the <a href="https://huggingface.co/byroneverson/internlm2_5-7b-chat-abliterated/blob/main/abliterate-internlm-2-5-7b-chat.ipynb">jupyter notebook</a> for details of how this model was abliterated from internlm2_5-7b-chat.
|
| 18 |
|
|
|
|
| 12 |
|
| 13 |
# internlm2_5-7b-chat-abliterated
|
| 14 |
|
| 15 |
+
## Version 1.1 (Updated 9/1/2024): Layer 17 is used for abliteration instead of 16. Refusal mitigation tends to work better with this layer. PCA and cosine similarity tests seem to agree.
|
| 16 |
|
| 17 |
Check out the <a href="https://huggingface.co/byroneverson/internlm2_5-7b-chat-abliterated/blob/main/abliterate-internlm-2-5-7b-chat.ipynb">jupyter notebook</a> for details of how this model was abliterated from internlm2_5-7b-chat.
|
| 18 |
|