Update README.md
Browse files
README.md
CHANGED
|
@@ -17,6 +17,8 @@ library_name: transformers
|
|
| 17 |
|
| 18 |
# gemma-2-27b-it-abliterated
|
| 19 |
|
|
|
|
|
|
|
| 20 |
This is a new approach for abliterating models using CPU only. I was able to abliterate this model using free kaggle processing with no accelerator.
|
| 21 |
1. Obtain refusal direction vector using a quant model with llama.cpp (llama-cpp-python and ggml-python).
|
| 22 |
2. Orthogonalize each .safetensors files directly from original repo and upload to a new repo. (one at a time)
|
|
|
|
| 17 |
|
| 18 |
# gemma-2-27b-it-abliterated
|
| 19 |
|
| 20 |
+
## Now accepting abliteration requests. If you would like to see a model abliterated, follow me and leave me a message with model link.
|
| 21 |
+
|
| 22 |
This is a new approach for abliterating models using CPU only. I was able to abliterate this model using free kaggle processing with no accelerator.
|
| 23 |
1. Obtain refusal direction vector using a quant model with llama.cpp (llama-cpp-python and ggml-python).
|
| 24 |
2. Orthogonalize each .safetensors files directly from original repo and upload to a new repo. (one at a time)
|