Update README.md
Browse files
README.md
CHANGED
|
@@ -4,6 +4,8 @@ license: llama3
|
|
| 4 |
---
|
| 5 |
# Llama-3-70B-Instruct-abliterated-v3 Model Card
|
| 6 |
|
|
|
|
|
|
|
| 7 |
[My Jupyter "cookbook" to replicate the methodology can be found here, refined library coming soon](https://huggingface.co/failspy/llama-3-70B-Instruct-abliterated/blob/main/ortho_cookbook.ipynb)
|
| 8 |
|
| 9 |
This is [meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) with orthogonalized bfloat16 safetensor weights, generated with a refined methodology based on that which 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.
|
|
|
|
| 4 |
---
|
| 5 |
# Llama-3-70B-Instruct-abliterated-v3 Model Card
|
| 6 |
|
| 7 |
+
## [Get v3.5 of this model instead!](https://huggingface.co/Meta-Llama-3-70B-Instruct-abliterated-v3.5-GGUF)
|
| 8 |
+
|
| 9 |
[My Jupyter "cookbook" to replicate the methodology can be found here, refined library coming soon](https://huggingface.co/failspy/llama-3-70B-Instruct-abliterated/blob/main/ortho_cookbook.ipynb)
|
| 10 |
|
| 11 |
This is [meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) with orthogonalized bfloat16 safetensor weights, generated with a refined methodology based on that which 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.
|