@[email protected] to [email protected]English • 20 hours agoCutting-edge Chinese “reasoning” model rivals OpenAI o1—and it’s free to downloadarstechnica.comexternal-linkmessage-square7fedilinkarrow-up130arrow-down10file-textcross-posted to: technology[email protected][email protected]
arrow-up130arrow-down1external-linkCutting-edge Chinese “reasoning” model rivals OpenAI o1—and it’s free to downloadarstechnica.com@[email protected] to [email protected]English • 20 hours agomessage-square7fedilinkfile-textcross-posted to: technology[email protected][email protected]
minus-square@[email protected]linkfedilink13•18 hours agoIs it able to generate text on Winnie the Pooh or how free Taiwan is without crashing though?
minus-squareGreyBeardlinkfedilink4•9 hours agoI did some locally hosted testing. It absolutely refused to talk about Tiananmen Square. But it was more than happy to talk about Kent State. Interesting what the model happens to think is safe and what it think is unsafe.
minus-squareFubarberrylinkfedilinkEnglish5•15 hours agoSupposedly their cloud hosted version will block those responses, but the local run version does not.
minus-squareThe Bard in Greenlinkfedilink2•edit-217 hours agoI was curious about the exact same thing, but it’s a 671B parameter model and I only have 3 GPUs.
minus-square@[email protected]linkfedilink2•16 hours agoThey have a 3GB model that is close to 4o model
Is it able to generate text on Winnie the Pooh or how free Taiwan is without crashing though?
I did some locally hosted testing. It absolutely refused to talk about Tiananmen Square. But it was more than happy to talk about Kent State. Interesting what the model happens to think is safe and what it think is unsafe.
Supposedly their cloud hosted version will block those responses, but the local run version does not.
It’s in the article.
I was curious about the exact same thing, but it’s a 671B parameter model and I only have 3 GPUs.
They have a 3GB model that is close to 4o model