aashish1904 commited on
Commit
1316775
1 Parent(s): a2e1c05

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +40 -0
README.md ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+
4
+ base_model: google/gemma-2-27b-it
5
+ pipeline_tag: text-generation
6
+ license: gemma
7
+ language:
8
+ - en
9
+ tags:
10
+ - gemma
11
+ - gemma-2
12
+ - chat
13
+ - it
14
+ - abliterated
15
+ library_name: transformers
16
+
17
+ ---
18
+
19
+ [![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory)
20
+
21
+
22
+ # QuantFactory/gemma-2-27b-it-abliterated-GGUF
23
+ This is quantized version of [byroneverson/gemma-2-27b-it-abliterated](https://huggingface.co/byroneverson/gemma-2-27b-it-abliterated) created using llama.cpp
24
+
25
+ # Original Model Card
26
+
27
+
28
+
29
+
30
+ # gemma-2-27b-it-abliterated
31
+
32
+ ## Now accepting abliteration requests. If you would like to see a model abliterated, follow me and leave me a message with model link.
33
+
34
+ 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.
35
+ 1. Obtain refusal direction vector using a quant model with llama.cpp (llama-cpp-python and ggml-python).
36
+ 2. Orthogonalize each .safetensors files directly from original repo and upload to a new repo. (one at a time)
37
+
38
+ Check out the <a href="https://huggingface.co/byroneverson/gemma-2-27b-it-abliterated/blob/main/abliterate-gemma-2-27b-it.ipynb">jupyter notebook</a> for details of how this model was abliterated from gemma-2-27b-it.
39
+
40
+ ![Logo](https://huggingface.co/byroneverson/gemma-2-27b-it-abliterated/resolve/main/logo.png "Logo")