Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32

This is an Abliterated version of Qwen3.5-4B using a modified version of Prometheus, then using Quanta and HugstonOne. Credit to https://huggingface.co/wangzhang and: https://github.com/ggml-org/llama.cpp but also Hugston team: https://github.com/Mainframework

The aim is to understand the safety mechanism of different llm models for research purposes.

Here we show proof of concept of how we can change the model behaviour preserving accuracy and lowering the refusal rate with very few trial which run in relatively small datasets. As a matter of fact it can run in a cheap laptop in cpu narrowing it down to 20 min for a small model.

6 trials Refusals: 48/1000, KL divergence: 0.0004 (keeps getting better :)

---

Credit to Alibaba_Qwen for the model creation

Credit to https://huggingface.co/wangzhang for abliteration method

Credit to LLama.cpp team for the great contribution

Credit to Hugston Team for Converting, Quantizing, Testing, Benching and other...

Credit to Huggingface for the amazing hosting platform

---

Keep away from children

Here we show the behaviour running the model in HugstonOne (the 0.8b, as an example).

The quantization in GGUF was made in f32 for beter quants.
Here we show Quanta our convertor and Quantizer tool.