---
base_model: internlm/internlm2_5-20b-chat
pipeline_tag: text-generation
license: apache-2.0
language:
  - en
  - zh
tags:
- interlm
- internlm2
- internlm2_5
- chat
- it
- abliterated
library_name: transformers
---



# internlm2_5-20b-chat-abliterated

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.
1. Obtain refusal direction vector using a quant model with llama.cpp (llama-cpp-python and ggml-python).
2. Orthogonalize each .safetensors files directly from original repo and upload to a new repo. (one at a time)

Check out the <a href="https://huggingface.co/byroneverson/internlm2_5-20b-chat-abliterated/blob/main/abliterate-internlm-2-5-20b-chat.ipynb">jupyter notebook</a> for details of how this model was abliterated from internlm2_5-20b-chat.

![Logo](https://huggingface.co/byroneverson/internlm2_5-20b-chat-abliterated/resolve/main/logo.png "Logo")