noctrex/Llama-3.3-8B-Instruct-128k-abliterated-GGUF

This is an abliterated version of Llama-3.3-8B-Instruct, made using Heretic v1.1.0

This is the model with 128k context.

The quantizations were created using an imatrix merged from combined_en_medium and harmful.txt to leverage the abliterated nature of the model.

Performance

Metric	This model	Original model
Refusals	5/100	95/100
KL divergence	0.0919	0

BibTeX entry and citation info

@misc{heretic,
  author = {Weidmann, Philipp Emanuel},
  title = {Heretic: Fully automatic censorship removal for language models},
  year = {2025},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/p-e-w/heretic}}
}