metadata

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.

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 internlm2_5-20b-chat.