Re:Bypass DeepSeek censorship by speaking in hex
by mmazing on Saturday February 01, 2025 @04:29PM
(#42902553)
Weird. Followup - I am getting censorship on the model from ollama's public model repository, but NOT from the models I got from huggingface running on a locally compiled llama.cpp.
[ Parent
| on HN ]
There are no comments on this comment yet.