metadata
pipeline_tag: text-generation
base_model: gemma-2-27b-it-abliterated
library_name: transformers
QuantFactory/gemma-2-27b-it-abliterated-GGUF
This is quantized version of byroneverson/gemma-2-27b-it-abliterated created using llama.cpp
Original Model Card
base_model: google/gemma-2-27b-it pipeline_tag: text-generation license: gemma language:
- en tags:
- gemma
- gemma-2
- chat
- it
- abliterated library_name: transformers
QuantFactory/gemma-2-27b-it-abliterated-GGUF
This is quantized version of byroneverson/gemma-2-27b-it-abliterated created using llama.cpp
Original Model Card
gemma-2-27b-it-abliterated
Now accepting abliteration requests. If you would like to see a model abliterated, follow me and leave me a message with model link.
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.
- Obtain refusal direction vector using a quant model with llama.cpp (llama-cpp-python and ggml-python).
- Orthogonalize each .safetensors files directly from original repo and upload to a new repo. (one at a time)
Check out the jupyter notebook for details of how this model was abliterated from gemma-2-27b-it.
