@moe90@feddit.nl to Technology@lemmy.worldEnglish • 3 months agoDoes DeepSeek Censor Its AI Answers? On These Sensitive Topics, Yes.www.forbes.comexternal-linkmessage-square23fedilinkarrow-up1126arrow-down19file-text
arrow-up1117arrow-down1external-linkDoes DeepSeek Censor Its AI Answers? On These Sensitive Topics, Yes.www.forbes.com@moe90@feddit.nl to Technology@lemmy.worldEnglish • 3 months agomessage-square23fedilinkfile-text
minus-square@LorIps@lemmy.worldlinkfedilinkEnglish3•3 months agoR1-32B hasn’t been added to Ollama yet, the model I use is Deepseek v2, but as they’re both licensed under MIT I’d assume they behave similarly. I haven’t tried out OpenAI o1 or Claude yet as I’m only running models locally.
minus-square@tyler@programming.devlinkfedilinkEnglish2•3 months agoHmm I’m using 32b from ollama, both on windows and Mac.
minus-square@LorIps@lemmy.worldlinkfedilinkEnglish2•3 months agoAh, I just found it. Alpaca is just being weird again. (I’m presently typing this while attempting to look over the head of my cat)
R1-32B hasn’t been added to Ollama yet, the model I use is Deepseek v2, but as they’re both licensed under MIT I’d assume they behave similarly. I haven’t tried out OpenAI o1 or Claude yet as I’m only running models locally.
Hmm I’m using 32b from ollama, both on windows and Mac.
Ah, I just found it. Alpaca is just being weird again. (I’m presently typing this while attempting to look over the head of my cat)