Update README.md
Browse files
README.md
CHANGED
|
@@ -6,9 +6,13 @@ license: apache-2.0
|
|
| 6 |
|
| 7 |
This is the **WizardLM-2-7B** model with orthogonalized bfloat16 safetensor weights, based on the implementation by `@failspy`. For more info:
|
| 8 |
|
| 9 |
-
- Original paper preview
|
| 10 |
- Jupyter notebook containing a implementation of the methodology, by `@failspy`: <https://huggingface.co/failspy/llama-3-70B-Instruct-abliterated/blob/main/ortho_cookbook.ipynb>
|
| 11 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
## Prompt Template
|
| 13 |
|
| 14 |
This model uses the prompt format from **Vicuna** and supports **multi-turn** conversation.
|
|
|
|
| 6 |
|
| 7 |
This is the **WizardLM-2-7B** model with orthogonalized bfloat16 safetensor weights, based on the implementation by `@failspy`. For more info:
|
| 8 |
|
| 9 |
+
- Original paper preview presenting the methodology: <https://www.alignmentforum.org/posts/jGuXSZgv6qfdhMCuJ/refusal-in-llms-is-mediated-by-a-single-direction>
|
| 10 |
- Jupyter notebook containing a implementation of the methodology, by `@failspy`: <https://huggingface.co/failspy/llama-3-70B-Instruct-abliterated/blob/main/ortho_cookbook.ipynb>
|
| 11 |
|
| 12 |
+
## GGUF Files
|
| 13 |
+
|
| 14 |
+
I will upload some GGUF files here: <https://huggingface.co/fearlessdots/WizardLM-2-7B-abliterated-GGUF>
|
| 15 |
+
|
| 16 |
## Prompt Template
|
| 17 |
|
| 18 |
This model uses the prompt format from **Vicuna** and supports **multi-turn** conversation.
|