235

This is how the censorship works in DeepSeek (lemmy.world)

submitted 6 days ago by jerryh100@lemmy.world to c/196

42 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[-] BaroqueInMind@lemmy.one 17 points 5 days ago* (last edited 4 days ago)

DeepSeek is okay, don't use it over others until more information about it comes out.

Can someone please recommend a good self-hosted llm model that isn't censored?

[-] AtHeartEngineer@lemmy.world 9 points 5 days ago

I'm sure someone will dolphin-ize it at some point

[-] BaroqueInMind@lemmy.one 13 points 5 days ago

What does that even mean? Can you please elaborate?

[-] Capsicones 10 points 5 days ago

You can look up Eric Hartford on Huggingface for more info.

Basically, somebody removes such restrictions from models, and publishes uncensored ones under the name "Dolphin". Presumably, an uncensored Deepseek would be called something like "Deepseek R1-dolphin". The full Deepseek R1 is quite large, and I'm not sure when this will happen yet. But there are other great Dolphin models.

Some models like Meta's Llama are way too censored to be useful for many completely normal use cases, and the guy is doing God's work in my opinion.

[-] AtHeartEngineer@lemmy.world 3 points 5 days ago

Agreed, and thanks for adding the background. Looks like someone abliterated deepseek already trying to make it "uncensored" but it sounds the process ruined the model.