News for hackers. Stuff that matters.

A comment on Show HN: I Created ErisForge, a Python Library for Abliteration of LLMs. Parent comment

Re:Show HN: I Created ErisForge, a Python Library for Ablite... by notavalleyman on Monday January 27, 2025 @12:55PM (#42843752)
No, youre mistaken. The model weights are not in any way censored. However, the web frontend has legal restrictions. When you're seeing posts about deepseek censorship, it's about the frontend and not the weights. As such, abliteration is irrelevant here
[ Parent | on HN ]
Re:Show HN: I Created ErisForge, a Python Library for Ablite... by animal_spirits on Monday January 27, 2025 @02:30PM (#42844705)
I am not claiming deepseek is censored. But these are tests to determine _if_ a model is censored. This would be a valid test for OpenAI models as well.
[ Parent | on HN ]
Re:Show HN: I Created ErisForge, a Python Library for Ablite... by genewitch on Monday January 27, 2025 @01:52PM (#42844356)
My qwen "weights" refuse to answer the question and my front end is uncensored. So, what you are saying sounds incorrect to me.
[ Parent | on HN ]
Re:Show HN: I Created ErisForge, a Python Library for Ablite... by notavalleyman on Monday January 27, 2025 @02:03PM (#42844460)
Qwen is different to deepseek. We were not talking about qwen. Abliteration might be a valid way to address what you're describing with qwen.
[ Parent | on HN ]
Re:Show HN: I Created ErisForge, a Python Library for Ablite... by genewitch on Monday January 27, 2025 @02:54PM (#42844950)
oh so this model deepseek-r1-qwen-distilled isn't deepseek? ok. Thanks. I have a quarter TB of models, i don't test every single one just to comment on HN, thanks though.
[ Parent | on HN ]