It looks super cool, any plan on open sourcing something? Btw, looking for an AI solution/sale engineer :P
68 karma · joined November 14, 2024
https://huggingface.co/blog/mlabonne/abliteration#%E2%9A%96%...
https://huggingface.co/blog/leonardlin/chinese-llm-censorshi...
Depend on what you mean by training, they change the weights.
> Do these techniques train models while performing the modifications?
I'm not sure I understand, but there is an example of performing an obliteration on gemma to make it never refuse an answer. It's about 10 lines of code.