https://huggingface.co/AiAsistent/gemma-3-4b-it-Cognitive-Liberty
#1632
by
Laetilia
- opened
https://huggingface.co/AiAsistent/gemma-3-4b-it-Cognitive-Liberty
I've found fine-tune of Gemma 3 4B that sounds really interesting to me (at least on paper)...
Using the Heretic LLM methodology and the custom Cognitive Liberty V3 dataset, this model removes refusals by teaching the AI deep reasoning, philosophical nuance, and high-level sociological analysis, rather than simply ablating safety layers.
I think it would be nice if you'll made GGUFs for it. Thank you!
It's queued!
You can check for progress at http://hf.tst.eu/status.html or regularly check the model
summary page at https://hf.tst.eu/model#gemma-3-4b-it-Cognitive-Liberty-GGUF for quants to appear.