Re:DeepSeek-R1 with Dynamic 1.58-bit Quantization
by greenavocado on Tuesday January 28, 2025 @09:26AM
(#42852628)
Would fine-tuning by using a LoRA paper over the censorship to a large degree?
[ Parent
| on HN ]
Re:DeepSeek-R1 with Dynamic 1.58-bit Quantization
by im3w1l on Tuesday January 28, 2025 @02:20PM
(#42856705)
Why even bother decensoring it (except academic curiosity ig)? There are a million other ways you can learn about those subjects.
The people making the model probably don't really give a shit about politics and just did the minimum to avoid being embarassed, but if people start jailbreaking it they will be forced to care.
Re:DeepSeek-R1 with Dynamic 1.58-bit Quantization
by greenavocado on Wednesday January 29, 2025 @08:09PM
(#42873590)
Because the best way to learn is through interrogation.
I don't give a damn about ideology I just want everything ever thought or written searchable and interactive