Hacker News new | ask | show | jobs
by DeepSeaTortoise 471 days ago
TBH, I REALLY like the tiny models. Like smollm2.

Also lobotomized LLMs ("abliterated") can be a lot of fun.

1 comments

I think you mean un-lobotomize, and apparently it can be done without retraining? Wild!

https://huggingface.co/blog/mlabonne/abliteration

Thanks for clarifying that. I can understand their take. But, I also think of the models without abliteration as lobotomized